CN114005424A

CN114005424A - Information processing method, information processing device, electronic equipment and storage medium

Info

Publication number: CN114005424A
Application number: CN202111085242.1A
Authority: CN
Inventors: 陈正扬; 苑盛成; 陈夏阳
Original assignee: Beijing Smart Sound Technology Co ltd
Current assignee: Beijing Smart Sound Technology Co ltd
Priority date: 2021-09-16
Filing date: 2021-09-16
Publication date: 2022-02-01

Abstract

The application discloses an information processing method, an information processing device, electronic equipment and a storage medium, and the specific implementation scheme is as follows: acquiring a composition template obtained based on music files, wherein the music files comprise files obtained by editing based on a Musical Instrument Digital Interface (MIDI); acquiring music information of a music to be edited; and obtaining a target object according to the music information and the composition template. By adopting the method and the device, the complete and reasonable compilation music can be automatically generated.

Description

Information processing method, information processing device, electronic equipment and storage medium

Technical Field

The present application relates to the field of computer music technologies, and in particular, to an information processing method and apparatus, an electronic device, and a storage medium.

Background

Since the information revolution, the way music and multimedia are spread has changed in a short time. This variety of qualities has led to a dramatic increase in market demand for various types of music: a great deal of original music is required regardless of whether the song, album, MV, karaoke, which is a major element of popular music or artistic creation, or short video, advertisement, animation, trailer, and movie works using music as an auxiliary, or radio, anchor, public space music using music as background content. How to automatically generate complete and reasonable editorial music becomes a technical problem to be solved urgently in the field.

Disclosure of Invention

The application provides an information processing method, an information processing device, electronic equipment and a storage medium.

According to an aspect of the present application, there is provided an information processing method including:

acquiring a music editing template obtained based on music files, wherein the music files comprise files obtained by editing based on Musical Instrument Digital Interface (MIDI);

acquiring music information of a music to be edited;

and obtaining a target object according to the music information and the composition template.

According to another aspect of the present application, there is provided an information processing apparatus including:

the template acquisition module is used for acquiring a music editing template obtained based on music files, wherein the music files comprise files obtained based on MIDI editing;

the information acquisition module is used for acquiring music information of a music to be edited;

and the synthesis processing module is used for obtaining the target object according to the music information and the composition template.

According to another aspect of the present application, there is provided an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method as provided by any one of the embodiments of the present application.

According to another aspect of the present application, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method provided by any one of the embodiments of the present application.

The method comprises the steps of obtaining a music editing template obtained based on music files, wherein the music files comprise files obtained based on MIDI editing; acquiring music information of a music to be edited; and obtaining a target object according to the music information and the composition template. By adopting the method and the device, the user can automatically generate the complete and reasonable musical composition only by inputting the music information (such as simple input chord, melody and other information) of the musical composition to be made through the pre-made musical composition template.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:

FIG. 1 is a schematic flow chart diagram of an information processing method according to an embodiment of the present application;

FIG. 2 is a schematic flow chart illustrating automatic composition in an application example according to an embodiment of the present application;

fig. 3 is a schematic view of a typical MIDI fragment in a piano roller shutter according to an application example of the embodiment of the present application;

FIG. 4 is a schematic diagram of a labeling result presented by labeling FIG. 3 in an application example according to an embodiment of the present application;

FIG. 5 is a diagram of multi-track MIDI engineering in an example application according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a segmentation of FIG. 5 in an application example according to an embodiment of the present application;

FIG. 7 is a diagram illustrating music information to be composed in an application example according to an embodiment of the present application;

fig. 8 is a flowchart illustrating automatic composition of changing accompaniment into solo according to an application example of the embodiment of the present application;

FIG. 9 is a schematic diagram of body length assignment in an application example according to an embodiment of the present application;

FIG. 10 is a diagram illustrating various effects of cycling and stretching from 8 slices to 16 slices for a 4-bin count in an example application according to an embodiment of the present application;

FIG. 11 is a diagram illustrating constraint parameters of a keyboard in an example application according to an embodiment of the present application;

FIG. 12 is a diagram illustrating constraint parameters of a guitar in an example application according to an embodiment of the present application;

fig. 13 is a schematic diagram of a piano playing segment chord transition in an application example according to the embodiment of the application;

FIG. 14 is a diagram illustrating search results of Cm9 and chords at the time of a six-note strut and chord in an application example according to the embodiment of the application;

FIG. 15 is a diagram illustrating selection of an optimal path in a multi-stage dynamic programming phase according to an embodiment of the present application;

FIG. 16 is a schematic illustration of an accompaniment in an application example according to an embodiment of the present application;

FIG. 17 is a diagrammatic illustration of a solo in an application example in accordance with an embodiment of the present application;

FIG. 18 shows an example of a pair t according to an embodiment of the present application_kSchematic diagrams further divided according to hand type;

fig. 19 is a schematic diagram of a composition structure of an information processing apparatus according to an embodiment of the present application;

fig. 20 is a block diagram of an electronic device for implementing the information processing method according to the embodiment of the present application.

Detailed Description

The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted for clarity and conciseness.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. The term "at least one" herein means any combination of any one or more of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C. The terms "first" and "second" used herein refer to and distinguish one from another in the similar art, without necessarily implying a sequence or order, or implying only two, such as first and second, to indicate that there are two or more of the features, first and second, and the first feature may be one or more of the other features.

Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present application. It will be understood by those skilled in the art that the present application may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present application.

In the related art, a large amount of music material is required for conventional audiovisual products such as advertisements, dramas, movies, and games, or emerging short videos, live broadcasts, and the like. With the development of various music platforms, more and more people become musicians and publish their own works on these music platforms. It can be said that music has become an indispensable part of human life.

Meanwhile, with the development of recording and manufacturing technologies, music can be made by adding a keyboard to a computer. Although there are apparatuses for music production, professional knowledge is still required, and in order to make a complete work, learning composition and mixing are required in addition to learning the musical theory to write a chord and assigning a chord to a melody. There are some systems available on the market that can implement automatic composition. They can be roughly classified into two types. The electronic organ is a traditional electronic organ, and the deep learning is a new type. The technical scheme of the electronic organ is widely applied to various performance occasions, and the electronic organ can use a preset key to play chords. There are also some products like the principle, such as the Box music, Band in a Box, etc. The product utilizes the property of chord musical scale to map the playing of one musical instrument under one chord to the playing of another chord, and then a plurality of music segments are connected, thereby achieving the effect of distributor writing. The technical scheme of the electronic organ generally uses a chord scale to change the springing method of one chord into another chord, and has the following problems: the chord and the musical scale are not in one-to-one correspondence, the same chord may correspond to different musical scales under different conditions, the mapping is performed mechanically, the result is single, and the originality is low. With the popularity of deep learning, the technical solutions of the deep learning class have some applications in music, for example, MuseNet is a model for generating multi-track music based on GPT2 neural network proposed by OpenAI in 2019. Through the training of a large number of music pieces, the neural network can predict the writing of notes of each track orchestrator of multi-track music in a given style. The technical scheme of the deep learning class has the following problems: the training amount requirement is huge in the training process, and the generated result lacks interpretability and controllability.

There are hundreds of musical instruments and hundreds of chords in the world, each chord has many arrangement modes on different musical instruments, and the possibility of composing music cannot be measured in consideration of smooth connection between different chord arrangement modes and matching between different musical instruments. While mixing sound requires intensive study of the infinite sound sources and mixing plug-ins by musicians and a great deal of experience accumulation. This undoubtedly costs much energy to the musician. Compared with the first impression of directly sensing the melody, the lyric and the like, the music composing and mixing do not need much innovation, and the music composing which is too gorgeous is too loud in many times. The threshold for music production is high, but music is greatly needed, so a technology for reducing the difficulty of music production is called for.

In view of the above dilemma, the information processing method provided by the present application is a technical scheme for automatically composing music based on a music composing template. On one hand, the music editing is a necessary way in the music production process, the related fields and theories are numerous, and a great deal of effort needs to be paid by people for learning the music editing; on the other hand, in popular music, the original part is mostly reflected in the melody, lyric and the like of the song, but not in the composition, that is, the composition has certain reusability, and there is a possibility of a multiplexing mode. The technical scheme can be used for manufacturing the song editing template in advance, mainly comprises a data preparation module and an automatic song editing module, the song editing template can be manufactured and marked by professional musicians, a user only needs to provide music information, such as simply inputting information of chords, melodies and the like, and then the song editing template can be migrated to new music information through calculation of the automatic song editing module to generate complete and reasonable songs, and a music digital file in an MIDI format can be exported.

According to an embodiment of the present application, an information processing method is provided, and fig. 1 is a flowchart of the information processing method according to the embodiment of the present application, and the method can be applied to an information processing apparatus, for example, in the case where the apparatus can be deployed in a terminal or a server or other processing device for execution, composition template acquisition, music file editing, and the like can be performed. Among them, the terminal may be a User Equipment (UE), a mobile device, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, and so on. In some possible implementations, the method may also be implemented by the processor invoking computer readable instructions stored in the memory. As shown in fig. 1, includes:

s101, acquiring a music editing template obtained based on music files, wherein the music files comprise files obtained based on musical instrument MIDI editing.

S102, music information to be edited is obtained.

In one example, the music information to be composed may include: paragraph, beat number, speed, mode, chord, melody, etc.

S103, obtaining a target object according to the music information and the music composition template.

In an example, the target object is a new music file obtained after the music composition process, for example, design requirements of a user-customized new music file can be obtained according to the music information of the music to be composed, and the new MIDI file is obtained by performing the music composition process in combination with materials that can be provided by an existing MIDI file in the music composition template (for example, materials that include paragraphs, bodies, segments, slices, track attributes, chords, and pitch attributes of each note obtained after the old MIDI file is split and labeled).

In an example, the composition processing can be implemented by an automatic composition system based on the composition template. The automatic composing system can be composed of two modules, namely a data preparation module and an automatic composing module. The data preparation module (which can be arranged at the cloud end or the terminal) is used for obtaining the compilation template according to the materials.

The automatic composing module is oriented to the terminal user and can be arranged on the terminal. As long as the terminal (electronic equipment such as mobile phone or computer) is installed with the automatic music editing module (or corresponding automatic music editing processing logic), the method is within the protection scope of the present application. When the end user retrieves the required composition template from the database and inputs the music information to be composed, a complete digital music file (such as the new MIDI file) can be generated by the automatic composition system, and then the new MIDI file is exported.

By adopting the method and the device, the music composing template obtained based on the music file can be obtained, the music file comprises the file obtained based on MIDI editing, the music information of the music to be composed is obtained, and the target object is obtained according to the music information and the music composing template, so that a user can automatically generate complete and reasonable music composing only by inputting the music information (such as simple input chord, melody and other information) of the music to be composed through the music composing template made in advance.

In one embodiment, the method further comprises: performing segmentation processing and attribute labeling on the music file to obtain the music editing template; wherein, the editing template comprises: paragraph, body, segment, slice, track, note. For example, when the music file is the existing old MIDI file, the segmentation process and the attribute labeling are performed to segment the existing old MIDI file to obtain the materials including the paragraph, the body, the segment, the slice, the track, the chord, and the pitch of each note.

In one embodiment, the obtaining a target object according to the music information and the composition template includes: according to the music information, carrying out structural reorganization and note pitch readjustment on each material contained in the composition template so as to realize composition processing and obtain the target object. For example, in the case where the music file is the existing old MIDI file, the music composition process is a process of obtaining the target object (a new MIDI file obtained after the music composition process) by reorganizing the respective materials obtained through the segmentation process and the attribute labeling, and re-adjusting the pitch attribute of each note according to the music information to be music composition.

In one embodiment, the method further comprises: obtaining the paragraph by performing the segmentation processing on the music file; each of said sections containing at least one of said fabric bodies; the length of the segment in each segment is the length of the fabric body where the segment is located. For example, the paragraph is a part of the musical composition expressing the whole emotion, and the "verse", "refrain", "bridge" and the like are referred to as paragraphs. The body refers to a structure in which several performance methods existing in one paragraph are stable. The segment is a segment obtained by further dividing the segment into smaller division granularities after being divided based on the division granularities of the segment and the tissue.

In one embodiment, the method further comprises: obtaining first labeling information related to a structure and second labeling information related to a pitch by labeling the attributes of the music file; wherein the first annotation information comprises: labeling information respectively aiming at the paragraphs; wherein, the attribute labeling of the fabric, the segment and the slice is used as a part of the labeling information of the paragraph for describing the structural attribute of the paragraph; the second annotation information includes: and respectively carrying out attribute labeling on the track and the notes to obtain labeling information. For example, for the first labeling information, for a paragraph, the category of the paragraph needs to be labeled, that is, the song master or the song refrain corresponding to the song, etc. At least one fabric body is arranged in one section; for the fabric body, each fabric body needs to be marked with information such as the maximum length, the minimum length, the priority of adjustment and whether the fabric body can be skipped, wherein the maximum length and the minimum length are allowed after the length of the fabric body is changed; aiming at the segment, whether the content played by the segment is the main melody or the empty segment or not is marked, and the used musical instrument is marked, wherein the length of the segment is the length of the fabric in which the segment is positioned; for a slice, the slice is the smallest strong and weak cyclic unit in the musical instrument performance, and the occupation type including any one of the start slice, the end slice, the fixed slice and the regular slice needs to be labeled. For another example, the second annotation information includes: and respectively marking track attributes and note attributes. Wherein the track attributes comprise musical instrument categories, ranges and the like; the note attributes include: and the attributes related to the pitch of the note, such as chord to which the note belongs, vocal part to which the note belongs, note type and the like.

In one embodiment, the obtaining the target object by performing structural reorganization and note pitch readjustment on each material included in the composition template according to the music information to implement composition processing includes: according to the paragraph corresponding to the music information of the music to be composed and the length of the organism thereof, structurally reorganizing each material contained in the composing template to obtain a plurality of segments matched with the paragraph and the length of the organism thereof, wherein the segments are the structural information forming the target object; and readjusting the note pitches of the segments one by one according to the music information to be composed to obtain the target object. For example, the first step: structural reorganization (i.e., rearrangement of the plurality of segments) is performed, that is, rearrangement is performed according to the paragraph of the music information to be composed and the body length thereof. Specifically, paragraph matching may be performed first, for example, paragraphs in a matching template are used to match paragraphs of the music information to be composed first; then, the length of the fabric body can be dynamically planned and distributed, for example, the length of each fabric body is distributed according to the length of the music information to be edited; finally, the plurality of segments may be rearranged according to the first label information associated with the structure (the rearrangement may be performed according to the performance piece). In the second step, segment-by-segment re-adjustment of note pitch (i.e., segment-by-segment pitch adjustment) is performed on the plurality of segments. Specifically, the pitch search may be performed first, and at this time, each segment already corresponds to a part of the chord of the music information to be edited, and then the pitch search is used to find all possible new segments; the resulting new segments can then be concatenated using dynamic rules, so that the target object (new MIDI file, which is already a complete new accompaniment) is already available. Further, the method can also comprise the following steps: for one performance segment in the music information to be composed, the accompaniment is changed into solo according to the requirement.

Application example:

the processing flow of the embodiment of the application comprises the following contents:

fig. 2 is a schematic flow chart of automatic composition in an application example according to an embodiment of the present application. The flow is divided into two parts of data preparation and music generation. In the data preparation, digital music is firstly made by musicians, then the works of the musicians are sliced and labeled by a labeling person (which can be the musicians) and information required by a generation algorithm is added, and finally the materials are stored in a database as a music editing template. In music generation, the user-oriented part selects a required template from a database, inputs music information to be composed into the system, and finally generates a complete digital music file by the automatic composition system. The flow is specifically described below.

Production of digital music by musicians in data preparation

In today's digital music era, most musical instruments have alternatives with MIDI output capabilities. For example, pianists can play with a MIDI keyboard, musicians can use power tubes, drummers can use electronic drums, and even string instruments (guitars, violins) and the like have special peripheral devices for the acquisition of MIDI signals. With the support of various powerful soft sound sources, only using MIDI has achieved an effect comparable to or even exceeding that of the recording of real musical instruments.

In the process, the MIDI signals can be recorded by a Digital Audio Workstation (DAW), and the operations of adjusting, replacing tone colors, mixing and the like can be conveniently carried out on the MIDI signals. Such digital music has taken a major component in modern music production and has been developed more rapidly than recording sound directly in a concert hall.

Fig. 3 is a schematic diagram illustrating a visualization of typical MIDI segments in a piano rolling shutter according to an application example of the embodiment of the present application, fig. 4 is a schematic diagram illustrating a labeling result presented by labeling fig. 3 in an application example according to an embodiment of the present application, referring to fig. 3-4, any one rectangle in fig. 3 may represent a note, the left and right sides of the note represent the start and stop time of the note, the vertical position of the note represents the pitch, and the strength of each note may be further distinguished by different identifiers (such as different color identifiers). FIG. 4 labels the chord progression and note type of FIG. 3. Where region 11 is labeled to represent chord tones and region 12 is labeled to represent bass tones.

Specifically, as shown in fig. 3, the typical MIDI file played by the MIDI keyboard includes not only the start and stop time, pitch and velocity of each note, but also information such as: 1) lyrics that vary with time; 2) a tone number that varies with time; 3) time-varying beat numbers; 4) a speed over time; 5) the name of each track; 6) the tone number of each track; 7) a control value varying with time within each track; 8) within each track, the start time, end time, pitch, and velocity of each note. In view of the calculations involved with performance content, the present application may enter music projects (as opposed to recordings) that allow only pure MIDI production. Besides this limitation, musicians can freely create in DAW without distinction from normal music production.

Secondly, the digital music obtained by the production is cut and labeled in the data preparation

Fig. 5 is a schematic diagram of a multi-track MIDI engineering in an application example according to an embodiment of the present application, as shown in fig. 5, the multi-track MIDI being composed of several MIDI tracks including piano, guitar, bass and drum tracks, each small rectangle representing a note, time from left to right, and the vertical position of the rectangle representing the pitch. Further, in addition to the information provided by the MIDI engineering drawings that is needed for the user to automatically compose, the engineering can be processed manually or by using other automated methods. Fig. 6 is a schematic diagram of a segmentation of fig. 5 in an application example according to an embodiment of the present application, and the example shown in fig. 6 includes two segments and two tissues. Correspondingly, what corresponds to the area 21 in fig. 5 is indicated by a segment, while what is indicated by the dashed line 22 is the division of the slice.

In the process, an existing MIDI project can be used as a basis for editing another song, and two steps are needed. First, to accommodate the editing task of any length, the MIDI project needs to be cut into small pieces and reorganized according to certain rules. Second, the chord progression, melody, etc. of each song are different, and therefore the pitch of each note in this reorganized new project also needs to be adjusted. The above segmentation and labeling are prepared for these two operations.

Segmentation and annotation are processes of disassembling existing music projects, and automatic composition is a process of reorganizing disassembled materials. The two processes are somewhat reciprocal. However, in order to reduce the system coupling as much as possible, the annotation may focus on the music information of the MIDI project itself as much as possible, not the algorithm information required for automatic composition. There have been some theories in music theory as to the structure of horizontal paragraphs and the pitch arrangement of the vertical direction of music. The annotation requires the annotator to analyze the MIDI project to complement and complete the music information.

With respect to the segmentation for the MIDI project, one MIDI project may be divided into two levels in time, which are "paragraphs" and "organizations", respectively. Each MIDI track is further divided into smaller granularities, in addition to paragraphs and bodies, called "slices". The paragraph is a part of the musical composition expressing the complete emotion, such as "master song", "refrain", "bridge paragraph" etc. in daily speaking are referred to as paragraphs. A body refers to a structure in which several performance methods exist in one paragraph, which is relatively stable. And slice refers to the smallest unit of strong and weak cycles in the musical instrument performance. Fig. 6 shows the result of the structure division of fig. 5. The passage is easier to judge in popular music. The organisation can also be determined from a thumbnail of the MIDI track. A slice is usually a section. All three are musically objective. The portion of a MIDI track within an organisation is referred to as a "performance fragment", or simply "fragment". The information of the segments can be divided into a musical notation in time and a chord in pitch. It is the various chord progression and playing methods that provide rich listening feeling for music.

For labeling the MIDI engineering, after the paragraphs, the body and the slices of the MIDI engineering are divided, music theory information needs to be further labeled. The music theory information includes both structural and pitch. The structural information refers to the paragraph, the body, the segment and the slice determined in the previous step, and the attributes (labeled attributes related to each structure of the paragraph, the body, the segment and the slice) to be set are respectively shown in table 1.

TABLE 1

Wherein a paragraph needs to indicate its category, i.e. the master song or the refrain, etc. corresponding to a song. At least one fabric body is arranged in one section. When migrating to a new song, the paragraph length may change, and thus be redistributed along with the individual body lengths. Each entity needs to specify the maximum and minimum lengths allowed after the change, the priority of the adjustment, whether it can be skipped, etc.

For each segment, it needs to indicate whether the content played by the segment is a main melody or an empty segment, and obviously, the two types of segments do not need to be generated when the segments are re-composed. Since different instruments may have different playing algorithms, the instrument used is indicated. The length of the segment is the length of the fabric body where the segment is located, after the fabric body is distributed with the length, the segment needs to be filled with the lengths, the filling mode has two modes, and the segment can be filled with any length by circulation (or tiling) and stretching, and matching with the grouping number. Finally, the segments between a tune are not independent of each other, so several common inter-segment relationships have been devised: copy, high/low octaves, bind, merge. Copying, namely high/low octaves, namely the literal meaning, binding means that the slices of the two segments are required to be in one-to-one correspondence when being regenerated, and merging means that if the two segments belong to the same track and are adjacent front and back, the two segments are merged into one large segment for generation. If a segment is considered a point, the segment relationship is an undirected edge between the points. As long as these edges do not create a closed loop, there is no conflict.

Slices are pieces of material used for filling. Since music is often played with flowers in specific locations, we have designed three special segments, start, end and stationary, which appear only in specific locations. The rest belong to regular slices.

In addition to the adjustment structure, in order for the automatic composition of the automatic composition system to conform to the chord of a new song, the pitch of notes of each performance segment needs to be adjusted. The automatic composition should be able to retain the musical performance information of each segment of the composition template in place of the chord progression information. Therefore, besides the structure information, it is necessary to label the pitch information of the MIDI project to specify to which chord and its nature each note belongs in particular. When playing, different instruments often have different playing preferences, so that the instrument of each track needs to be marked. In addition, since it is customary for the user to play a bass note of a chord at a fixed position of the slice, and to play a note other than the chord, it is necessary to note the category of each note. In the pitch-related annotation attribute example of the present application, the attributes of the track and the attributes of the note are shown in table 2.

Track	Musical notes
		Musical instrument categories: keyboard, guitar, etc	The chord
Register	The sound part
			Note type: bass, chord, mode, fixation

TABLE 2

Wherein the track needs to indicate the instrument used and the register of this instrument. Each note needs to indicate the chord and the vocal part to which it belongs, and the type of note. Common note types include bass, chord tonic, tonality tonic and fixed pitch. Fixed pitch, i.e. before and after automatic composing, is constant, e.g. the notes of a drum set are constant. If the key type inner tones are labeled, the selectable range of the tone after the chord is replaced is any number in the key type (usually 7 to 8 candidates), and if the chord inner tones are labeled, the tone after the chord is replaced can only select the tones in the chord (usually 3 to 7 candidates), but the tone of the bass is labeled, and the selectable range only has 1 bass tone of the new chord. Fig. 4 is an example of segment notation, which is labeled chord progression, and each note is represented by area 11 for chord tonic and 12 for bass.

At this point, the data preparation process is completed, and a MIDI music project, structure division, attributes of paragraphs, bodies, clips, slices, tracks, chord progression, and attributes of each tone as a whole may be stored in the database as a composition template.

Inputting music information to be edited into automatic music editing system in music generation

In order to apply the previously labeled MIDI project, the music information should include paragraph, beat number, speed, mode, chord and melody. Fig. 7 is a schematic diagram of music information to be composed in an application example according to an embodiment of the present application, and as shown in fig. 7, an example of the music information to be composed includes paragraph, speed, beat number, key, chord and melody information.

Fourthly, generating a complete digital music file by an automatic music composing system in the music generation

In the process, after the music composing template can be selected and the music information is input, the system can automatically compose music according to the music composing template and the music information. In order to apply the complete composition template to a new song, a two-step operation is required. The first step, rearranging the slices. I.e. the slices are rearranged according to the passage of the new song and its length. Specifically, the paragraphs in the matching template are first used to match the paragraphs of the new song, then the lengths of the respective bodies are allocated according to the new lengths, and the slices are arranged piece by piece. And secondly, adjusting the pitch segment by segment. At the moment, each segment is already corresponding to a part of chord of the new song, all possible solutions are searched by using pitch search, and then the possible solutions are connected by using a dynamic programming algorithm to obtain the new segment. In this way, a complete new accompaniment is already available.

Fig. 8 is a flow chart of automatic composition of changing the accompaniment into the solo according to an application example of the embodiment of the present application, and as shown in fig. 8, for one performance segment, the accompaniment can also be changed into the solo as needed. The operation of each main step is described in detail below.

In the case of paragraph matching, the songs to be composed, the paragraphs and their order, etc. may be different from the template, and thus it is desirable that the template covers as many paragraph types as possible so that they can be matched when used.

For dynamically planning and allocating the length of the body, after the length of the paragraph is specified by a new song, if a plurality of bodies exist in the paragraph of the template, the length of the bodies in the paragraph needs to be reallocated. Fig. 9 is a schematic diagram of fabric length assignment in an application example according to an embodiment of the present application, and all the adjustment priorities of the fabric lengths are equal in the example shown in fig. 9. As a rule of thumb, the length of the body is usually 4 and its multiple acoustically more complete, so when changing the length of the paragraph, the assignment algorithm can satisfy the condition as much as possible: 1) the original length proportion of each fabric body is maintained as much as possible; 2) each body is taken as many as 4, for example, two bodies with 4+4 knots are used, and the total length is 10 knots, and the 4+6 knots are better to be allocated than the 5+5 knots; 3) some fabrics are more versatile, and therefore the length of these fabrics should be changed first when changing the length. For this reason, the fabric-related attributes in the label can be fully utilized to reassign lengths to fabrics. Three layers of priority levels are designed, and the fabric bodies with high priority levels are adjusted when the length is changed, and the fabric body length of the next priority level cannot be changed until the length of the fabric bodies reaches the limit. If the new paragraph is longer than the original, only the following may be possible:

a. the requirement can be met only by adjusting the paragraphs with the first priority, and the lengths of the second and third levels of tissues are unchanged;

b. all the first stages are set as maximum lengths, all the third stages are unchanged in length, and the second stage is redistributed;

c. the first and second levels are maximum length, and the third level is redistributed.

d. Cannot meet the requirements.

The situation is similar when the new paragraph is shorter than the original paragraph. Therefore, in the case where the requirement can be satisfied, it is only necessary to allocate between fabrics of the same priority, and thus the above-described condition 3) is satisfied.

Assuming that the priority to be adjusted is p, all the tissues smaller than p are set as the limit value, and all the tissues larger than p maintain the original length. For fabric with priority p, dynamic programming can be used for allocation. The dynamic programming equation is as follows:

where f (n, l) is the score for the first n tissues taken into account and a total length of l hours, w_n(k) Is the score for the nth tissue length taken at k hours. w is a_n(k) It is only necessary to satisfy two conditions, one is that the score is higher when the distribution is close to the proportion, and the other is that the score is higher when the distribution is a multiple of 4. The value range of k can be easily obtained from the minimum and maximum lengths in the attribute of the fabric label, and whether the three values can be skipped or not.

For the arrangement of slices according to the label, i.e. the slices are rearranged segment by segment, the length of the tissue distribution obtained from the previous step is the length of each track segment. It is then necessary that each segment fills up this length with a respective slice. First, because of the existence of the segment relationship, each segment may have a dependency (e.g., copy relationship, copy source), and because the segment relationship is required to be loop-free during labeling, the source (root node) of the segment relationship can always be found, and the segments can be generated preferentially. In order to increase the diversity of the arrangement results, the concept of slice grouping, i.e., the number of groups in the label, is introduced. Slices belonging to the same group may be replaced with each other. According to the label, the filling mode of the paragraph is two modes of circulation and stretching, which respectively correspond to the stable segment and the fade-in/fade-out segment of the music. The definition of the grouping is different according to the cycle and the stretching. In the round robin scheme, the number of packets refers to the length of a round robin section. In the stretching method, the number of groups means the number of layers of strength. Fig. 10 is a diagram illustrating different effects of cycling and stretching from 8 slices to 16 slices when the number of packets is 4 in an application example according to an embodiment of the present application, and in the example shown in fig. 10, squares represent slices and numbers represent packets. The slices of the same group can be replaced mutually, and different effects of prolonging by one time in circulation and stretching are respectively shown when the original length is the same and the grouping number is the same.

To this end, the structure and rhythm portion of the automatic composition has been completed, and then the pitch needs to be adjusted piece by piece.

With pitch search, it is meant an algorithm that reasonably migrates to a new chord sequence, while preserving the original segment notation. By the algorithm, a large number of results of the same playing segment after chord transformation can be quickly obtained, and meanwhile, the segments not only meet the requirements of a new chord sequence, but also keep the body of the original segment and meet the playing manipulation of a specific musical instrument. The process of the pitch search algorithm is described in detail below.

1. Constraint of labels

Firstly, after the new music information is obtained and input based on the third step, the new chord after the migration to which each tone belongs is divided by time, and then the marking information obtained by the second step is used, the selectable range of each tone can be obtained and is marked as M_pWhere p traverses each note in the performance segment, i.e., the pitch selectable range of each note under the new chord sequence. And let M be { M ═ M_p|p＝0,...,N_p-1}, wherein N_pIs the total number of tones in the performance section.

2. Restraint of musical instrument

The performance section is obtained by human playing through the musical instrument. Because the music instrument is inevitably restricted by human body posture and motion during playing, the structure of the music instrument determines the stacking mode of the tones which can be played by the music instrument. For example, it is easy to play five tones of CDEFG simultaneously on a keyboard-like instrument, but it is almost impossible on a guitar. To address this limitation, a set of restraint systems needs to be established.

The general form of the constraints is as follows. Total number of tones N given_pThe constraint G is:

wherein H_p,nIs a set of integers, represented in the nth set of constraint schemes G_nNext, the optional range of the p-th tone. N is a radical of_GIs the total number of constraint schemes. The following is a specific form of the above-described constraint, i.e., the hand shape when playing the musical instrument.

Fig. 11 is a schematic diagram of a constraint parameter of a keyboard in an application example according to an embodiment of the present application, and fig. 12 is a schematic diagram of a constraint parameter of a guitar in an application example according to an embodiment of the present application, and numbers indicate a half-tone interval. Referring to FIGS. 11-12, the positive integer N may be ordered_hRepresenting the number of "hands" required to play the instrument. Positive integer N_f,hThe number of "fingers" that can be allowed for the h-th hand, i.e., the maximum number of tones that can be simultaneously sounded. Vector I_h＝(I_0,h,I_1,h,I_2,h,...,I_Nf,h-1,h) The "center of motion" of each "finger" for each hand, i.e., the pitch aligned relative to the lowest note of that hand. Finally by R_min，R_maxTo constrain the movable pitch range of each finger to be R_min,R_max]. For common instruments, appropriate parameters can be selected for description. For example, for a keyboard-like musical instrument, N may be desirable_h＝2，N_f,0＝N_f,1By comparing finger width with the width of a normal keyboard, I can be set at 5₀＝p₀+(0,2,4,6,8)，I₁＝p₁+(0, 2,4,6,8)，R_min＝-3，R _max3 where p₀And p₁The pitches are corresponding to the roots of the fingers of the little finger of the left hand and the big finger of the right hand respectively. While for a guitar, N may be set_h＝1，N_f,0＝6，I＝p+(0,5, 10,15,19,24)，R_min＝0，R_maxP is the pitch of the index finger on the six strings, 3. Fig. 11-12 show the source of the various parameters on the keyboard and guitar, respectively. For string quartet, although a single instrument is basically a single instrument that cannot be composed and sounded, string quartet can be viewed as the performance of four "hands" on a keyboard, and thus, the string quartet is viewed as a four-handed performanceAppropriate parameters may also be selected for modeling.

In the actual playing process, all fingers cannot be placed on the musical instrument all at once, and certain fixed hand shapes are usually provided for the tones with specific numbers. For example, when only 5 tones are played, the piano often uses the little finger of the left hand, the index finger and the thumb, middle finger and little finger of the right hand to complete the performance, so that one hand type can be represented by one subset of I. The hand shape may be enumerated by a permutation combination when the total number of tones is known, or may be preset in advance.

3. Conversion method

FIG. 13 is a schematic diagram of a piano playing segment and chord transition in an application example according to an embodiment of the present application, and as shown in FIG. 13, { m } for a piano playing segment_iIs the original chord sequence within this segment, { n }_jIs the new sequence of chords that it is desired to migrate to. This is a many-to-many conversion problem, and the two sets of time points can be merged to set t_kFocus on only one of them, reducing the problem to a one-to-one conversion problem. The problem of many-to-many is solved as long as the problem of one-to-one can be solved and the problem of many-to-many is solved by one-to-one. In addition, two assumptions are made. 1) Before conversion, if two belong to the same t_kIf the pitch of the sound is the same, the same sound should be kept after conversion. 2) Two belonging to the same t_kIf the pitch of one of the tones is higher than that of the other tone, the pitch after the conversion of the first tone cannot be lower than that of the second tone. P represents the pitch before conversion, q represents the pitch after conversion, and the above condition can be noted as C:

under this assumption, the original problem becomes a search problem and can be solved by depth-first search. The pseudo code is as follows:

wherein, defining a depth-first search function search:

wherein N is_p,kIs t_kTotal number of notes in (1). After searching, each t can be obtained_kThe series of bullet methods can meet the requirements of chord migration and hand type constraint. Fig. 14 is a search result illustration diagram of Cm9 and chord at the time of columnar chord of six tones in an application example according to the embodiment of the present application, and as shown in fig. 14, a part of the search result of Cm9 at the time of columnar chord of six tones is basically ergonomic.

For connecting new segments using dynamic rules, i.e. dynamically planned concatenation, each t is searched for by the pitch of the previous step_kSeveral search results can be found as alternatives. An expert system is formed by scoring such as music analysis, simulated performance and the like, and then a dynamic programming algorithm is used, so that the selection of segments which have good effects and meet the aesthetic quality of the masses and are smoothly connected front and back can be realized, and the performance segments under the new chord sequence can be obtained.

Fig. 15 is a schematic diagram illustrating selection of an optimal path in a multi-stage dynamic planning stage according to an embodiment of the present application, where t may be t as shown in fig. 15_kThe search result is denoted as c_l,kEach of c_l,kAre all of a length N_p,kVector of (2), representing t_kA set of results for all tones. And finding an optimal path in the multi-stage dynamic planning stage, wherein the dotted line is a possible path, and the solid line represents the optimal path.

Because each t_kMay be too many to be suitable for direct searching, and thus may ignore the cross-t_kConsidering only t_kMass of itself, and adjacent t_kThe quality of the connection between the two parts. Thus, the optimal path problem is fullWhich is sufficient for optimal substructure properties and thus can be solved using dynamic programming. Expressed by f (l, k) when considering only t₀,t₁,...,t_k-1,t _k And ending at c_l,kThen the dynamic programming equation can be obtained as follows:

wherein, w (c)_l’,k-1,c_l,k) Is to evaluate a connection quality evaluation function between any two search results, and v (c)_l,k) Is a function of evaluating the quality of a search result itself. Thus, the final optimal path can pass max (f (l, N)_k-1)) to obtain. The form of w and v may not be fixed and may also contain parameters necessary for the generation. For example, for function v, there may also be the following requirements:

a. the user can not play a frame with the main melody, and if the user plays the frame, the user deducts the mark.

b. And satisfying the low range limit of the musical instrument timbre, and deducting if the musical instrument timbre does not satisfy the low range limit.

c. All notes should appear as early as possible from front to back, so as to clarify the chord attributes.

d. And adding and subtracting points according to the color preference parameters specified in the generation. For example, the more chord tones may be scored when the demand is a simple and clear accompaniment, but the more chord tones may be scored when the demand is a complex harmony such as jazz.

For the connection quality evaluation function w, the following requirements may also be made:

a. and according to whether the generated parameters are stable or not, adding points or subtracting points to the degree of the variation of the sound domains connected in front and back.

b. Considering how strongly the hands change, it is generally better to make the size smaller.

c. For the outer sound parts of polyphonic instruments, it is generally preferable that the connection is smoother, and the upper and lower outer sound parts are more opposite than the same direction.

The v and w functions can be further refined to form an expert system. In this way, an optimal connection in the sense of these two functions can be obtained.

The accompaniment is an optional part in terms of changing the accompaniment to a solo as required, taking into account that there is sometimes a need for a generator music solo. In this case, further post-processing is required to convert the polyphonic musical instrument of the previous step into a solo of the polyphonic musical instrument as the main melody accompaniment. Fig. 16 is a schematic diagram of the accompaniment in an application example according to the embodiment of the present application, fig. 17 is a schematic diagram of the solo in an application example according to the embodiment of the present application, and referring to fig. 16-17, an example of accompaniment segments can be obtained through the above pitch adjustment steps, which are shown in fig. 16 together with the pitch distribution of the main melody. Even if they are played on the same MIDI instrument, it still appears that two instruments are playing, and the conversion of the accompaniment plus the main melody into the solo of the polyphonic instrument as shown in fig. 17 starts mainly from two aspects of rhythm and range.

In most cases, the main melody is arranged in the treble part in order to highlight the listening impression of the melody. Therefore, the conversion method proposed in the present application considers only the case where the "hand" with the highest pitch is used to play the high-pitched part. After a polyphonic musical instrument is accompanied by the above steps, only the notes responsible for the "hand" responsible for the highest-pitch part are adjusted to obtain the solo. When a person plays a solo, the person is often influenced by the main melody to change the rhythm of the accompaniment notes so that the rhythm of the accompaniment notes is consistent with the main melody. Secondly, since a hand is required to play the melody and the chord at the same time, their range of the scale is limited by the shape of the hand. By the two-step adjustment, the effect of being compared like a single-playing can be obtained. The conversion process of the accompaniment into the solo will be described in detail below.

First, the note played by the original highest pitch "hand" (e.g., the right hand of a piano) is found first and a main melody is attached thereto, as shown in fig. 16. Then, for the melody on the beat, if there are accompaniment notes in the 16 minutes before and after the melody, the accompaniment notes are adjusted to be near the melody. Finally, an algorithm using hand-type rearrangement fingering.This conversion process is similar to the pitch search and dynamic programming concatenation process described above, but differs in that: because the melody needs to be played simultaneously, it is possible to play the melody at the same time t_kWithin the range, only one hand type can not meet the requirement, and the hand type needs to change along with the main rotation law. However, in the actual playing process, the hand shape is not required to be changed for each melody note, but is not changed as much as possible. It is therefore necessary here to determine which ranges use only one hand, i.e. for t_kFurther subdivided, fig. 18 is a schematic diagram of further dividing tk according to hand type in an application example according to the embodiment of the present application, as shown in fig. 18, at t_kIn the process of further division according to the hand types, once the subdivided range can be determined, the arrangement of the accompaniment sounds can be replanned completely according to the steps of pitch search and dynamic programming connection.

A greedy search strategy for determining single-hand coverage is described below. The basic idea of the strategy is to find t_kStarting from the highest pitch of the corresponding main melody, finding the maximum range which can be covered by the hand shape on the basis that the highest pitch in the hand shape plays the melody, and continuing the process in the rest part if the melody pitches in the front part and the back part are remained. The pseudo code is as follows:

function get _ range defining the recursive search range:

through the recursive algorithm, the hand type which is kept as still as possible can be found, the pitch searching process can be carried out again through the hand type (namely Gm), and the accompaniment can be converted into the solo through dynamic planning. At this time, the dynamically planned w and v functions can be adjusted appropriately due to the limitation of the main melody.

By this point, the automatic composition is complete and the MIDI files can be exported for DAW playback and audio file generation.

The above processing flows of the application example have the following advantages:

the application designs an automatic song editing flow and algorithm based on the existing MIDI engineering. By the method, an existing song composition can be easily applied to music to be edited, the conversion process is efficient, and a solo mode is supported. The user does not need to know the knowledge related to the music orchestrator, and the production efficiency of the music is greatly improved. Moreover, the following advantages are provided:

1. different parameters can be used for achieving the playing effect of different musical instruments;

2. by using dynamic programming, the optimal effect under the generation parameters can be achieved, and the originality is higher;

3. the style, paragraph, complexity, etc. of the generated result are highly controllable;

4. the method can be converted into a solo of a musical instrument, and the conversion result conforms to fingering of human;

with the support of the automatic song compiling system, song compiling becomes efficient and reasonable. Can be applied in many fields. Firstly, the difficulty of music production can be greatly reduced by adopting the application, so that musicians can put the strength in places really needing music inspiration concentration. After the music sample is rapidly made, the inspiration of the musicians can be further stimulated. Some music styles, such as rap, are words of choice after the prior accompaniment, and secondly, the application can be used for quickly making the accompaniment meeting the needs of the musicians. And a marked template can be repeatedly used, so that the efficiency of music production can be greatly improved.

In the aspect of video dubbing, the existing videos are dubbed by adopting the existing music. However, with existing music, in addition to possibly creating copyright issues, the music itself is likely not to fit well with the length, atmosphere and tempo of the video. However, it is obviously impractical to require all video producers to master the music production and to match their own video. By utilizing the automatic song editing system, the time points such as styles, paragraphs and the like can be selected by self, so that the dubbing music conforming to the video can be conveniently made. Since the last output MIDI file is ergonomic, it is actually playable. Therefore, the present application can adapt existing music to instrumental music solo tunes, which can be used in musical instrument teaching. The process of segmenting and marking is a process of disassembling a music project, and the process can enable a marking person to fully learn the writing method of the music person and is a good tool for composing music.

Because the automatic composition of the application has high generation speed and all parameters are controllable, the real automatic player can be realized by matching with deep learning music writing on the basis of the application. The sensor can also be used for sensing the environment and generating music conforming to the surrounding environment in real time.

According to an embodiment of the present application, there is provided an information processing apparatus, and fig. 19 is a schematic diagram of a configuration of the information processing apparatus according to the embodiment of the present application, and as shown in fig. 19, the information processing apparatus includes: a template obtaining module 51, configured to obtain a composition template obtained based on music files, where the music files include files obtained based on musical instrument MIDI; the information acquisition module 52 is used for acquiring music information to be edited; and the synthesis processing module 53 is configured to obtain a target object according to the music information and the composition template.

In one embodiment, the music editing system further comprises a segmentation and labeling module, which is used for performing segmentation processing and attribute labeling on the music file to obtain the music editing template; wherein, the editing template comprises: paragraph, body, segment, slice, track, note.

In an embodiment, the composition processing module is configured to, according to the music information, structurally reorganize each material included in the composition template and readjust a pitch of a note, so as to implement composition processing, and obtain the target object.

In one embodiment, the segmenting and labeling module is further configured to perform the segmenting process on the music file to obtain the paragraph; each of said sections containing at least one of said fabric bodies; the length of the segment in each paragraph is the length of the fabric body in which the segment is located.

In one embodiment, the segmenting and labeling module is further configured to perform attribute labeling on the music file to obtain first labeling information related to a structure and second labeling information related to a pitch; wherein the first annotation information comprises: labeling information respectively aiming at the paragraphs; wherein, the attribute labeling of the fabric, the segment and the slice is used as a part of the labeling information of the paragraph for describing the structural attribute of the paragraph; the second annotation information includes: and labeling information obtained by labeling the attributes of the track and the notes respectively.

In one embodiment, the composition processing module is configured to perform structural reorganization on each material included in the composition template according to a paragraph and an organization length thereof corresponding to the music information to be composed, to obtain a plurality of segments matched with the paragraph and the organization length thereof, where the plurality of segments are structural information constituting the target object; and readjusting the note pitch of the segments one by one according to the music information to be edited to obtain the target object.

The functions of each module in each apparatus in the embodiment of the present application may refer to corresponding descriptions in the above method, and are not described herein again.

According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.

Fig. 20 is a block diagram of an electronic device for implementing the information processing method according to the embodiment of the present application. The electronic device may be the aforementioned deployment device or proxy device. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.

As shown in fig. 20, the electronic apparatus includes: one or more processors 801, memory 802, and interfaces for connecting the various components, including a high speed interface and a low speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output device (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). Fig. 20 illustrates an example of a processor 801.

The memory 802 is a non-transitory computer readable storage medium as provided herein. The memory stores instructions executable by at least one processor, so that the at least one processor executes the information processing method provided by the application. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to execute the information processing method provided by the present application.

The memory 802, which is a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the information processing methods in the embodiments of the present application. The processor 801 executes various functional applications of the server and data processing by running the non-transitory software programs, instructions, and modules stored in the memory 802, that is, implements the information processing method in the above-described method embodiments.

The memory 802 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 802 may include high speed random access memory and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 802 optionally includes memory located remotely from the processor 801, which may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device of the information processing method may further include: an input device 803 and an output device 804. The processor 801, the memory 802, the input device 803, and the output device 804 may be connected by a bus or in another manner, and are exemplified by a bus in fig. 20.

The input device 803 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of the electronic device, such as a touch screen, keypad, mouse, track pad, touch pad, pointer stick, one or more mouse buttons, track ball, joystick, or other input device. The output devices 804 may include a display device, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.

Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.

The above-described embodiments should not be construed as limiting the scope of the present application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions are possible, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An information processing method, characterized in that the method comprises:

acquiring a music editing template obtained based on music files, wherein the music files comprise files obtained based on MIDI editing of a musical instrument digital interface;

acquiring music information of a music to be edited;

2. The method of claim 1, further comprising:

performing segmentation processing and attribute labeling on the music file to obtain the music editing template; wherein the content of the first and second substances,

the composing template comprises: paragraph, body, segment, slice, track, note.

3. The method of claim 1, wherein obtaining the target object according to the music information and the composition template comprises:

according to the music information, carrying out structural reorganization and note pitch readjustment on each material contained in the composition template so as to realize composition processing and obtain the target object.

4. The method of claim 2, further comprising:

obtaining the paragraph by performing the segmentation processing on the music file;

each of said sections containing at least one of said fabric bodies;

the length of the segment in each paragraph is the length of the fabric body in which the segment is located.

5. The method of claim 2, further comprising:

obtaining first labeling information related to a structure and second labeling information related to a pitch by labeling the attributes of the music file; wherein the content of the first and second substances,

the first annotation information includes: labeling information respectively aiming at the paragraphs; wherein, the attribute labeling of the fabric, the segment and the slice is used as a part of the labeling information of the paragraph for describing the structural attribute of the paragraph;

the second annotation information includes: and respectively carrying out attribute labeling on the track and the notes to obtain labeling information.

6. The method according to claim 3, wherein the performing of the composition process by structurally reorganizing each material contained in the composition template and adjusting the pitch of the note according to the music information to obtain the target object comprises:

according to the paragraph corresponding to the music information to be composed and the length of the organism thereof, structurally reorganizing each material contained in the composition template to obtain a plurality of segments matched with the paragraph and the length of the organism thereof, wherein the plurality of segments are structural information forming the target object;

and readjusting the note pitch of the segments one by one according to the music information to be edited to obtain the target object.

7. An information processing apparatus characterized in that the apparatus comprises:

the template acquisition module is used for acquiring a music editing template obtained based on music files, wherein the music files comprise files obtained based on Musical Instrument Digital Interface (MIDI) editing;

8. The apparatus of claim 7, further comprising a segmentation and labeling module configured to:

the composing template comprises: paragraph, body, segment, slice, track, note.

9. The apparatus of claim 7, wherein the composition processing module is configured to:

10. The apparatus of claim 8, wherein the segmentation and labeling module is further configured to:

each of said sections containing at least one of said fabric bodies;

11. The apparatus of claim 8, wherein the segmentation and labeling module is further configured to:

12. The apparatus of claim 9, wherein the composition processing module is configured to:

13. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-6.