CN112509581A

CN112509581A - Method and device for correcting text after speech recognition, readable medium and electronic equipment

Info

Publication number: CN112509581A
Application number: CN202011311695.7A
Authority: CN
Inventors: 姚佳立; 边俐菁
Original assignee: Beijing Youzhuju Network Technology Co Ltd
Current assignee: Beijing Youzhuju Network Technology Co Ltd
Priority date: 2020-11-20
Filing date: 2020-11-20
Publication date: 2021-03-16
Anticipated expiration: 2040-11-20
Also published as: CN112509581B

Abstract

The disclosure relates to a method and a device for correcting errors of texts after voice recognition, a readable medium and electronic equipment, which belong to the field of voice recognition and can improve the sentence accuracy rate of voice recognition. A method for correcting errors of a text after speech recognition comprises the following steps: checking whether the text after voice recognition belongs to the text of the characters in the words or not based on the expression characteristics of the text of the characters in the words; if the text after the voice recognition belongs to a word text in words, extracting words needing to be corrected and words used for correcting the words needing to be corrected from the text after the voice recognition, wherein the words needing to be corrected and the words used for correcting the words needing to be corrected are in a word-in-word relationship; searching candidate characters for correcting the character to be corrected from the corrected characters by using a pronunciation confusion matrix, wherein the pronunciation confusion matrix comprises the probability that each pronunciation is recognized as other pronunciations; the word to be error corrected is error corrected using the candidate word.

Description

Method and device for correcting text after speech recognition, readable medium and electronic equipment

Technical Field

The present disclosure relates to the field of speech recognition, and in particular, to a method and an apparatus for correcting a text after speech recognition, a readable medium, and an electronic device.

Background

With the popularization of intelligent devices and the development of natural language processing technologies, voice input becomes an increasingly important human-computer interaction means due to the characteristics of convenience and rapidness. However, due to the complexity of the language and the influence of the surrounding noise, the speech recognition result often has a large deviation from the content that the user actually wants to input, and further error correction processing needs to be performed on the text after speech recognition, so that the speech recognition result can be applied to an actual system.

Therefore, how to provide a text error correction scheme after speech recognition can effectively solve the problem of inaccurate speech recognition, which is a technical problem to be solved urgently at present.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

In a first aspect, the present disclosure provides a method for correcting a text after speech recognition, including: checking whether the text after voice recognition belongs to the text of the characters in the words or not based on the expression characteristics of the text of the characters in the words; if the text after the voice recognition belongs to a word text in words, extracting words needing to be corrected and words used for correcting the words needing to be corrected from the text after the voice recognition, wherein the words needing to be corrected and the words used for correcting the words needing to be corrected are in a word-in-word relationship; searching candidate words for correcting the word needing to be corrected from the words for correcting the word needing to be corrected by using a pronunciation confusion matrix, wherein the pronunciation confusion matrix comprises the probability that each pronunciation is recognized as other pronunciations; and correcting the word needing to be corrected by using the candidate word.

In a second aspect, the present disclosure provides an apparatus for correcting a text after speech recognition, including: the checking module is used for checking whether the text after the voice recognition belongs to the text of the characters in the words or not based on the expression characteristics of the text of the characters in the words; the extraction module is used for extracting a word needing to be corrected and a word used for correcting the word needing to be corrected from the text after the voice recognition if the text after the voice recognition belongs to a word text in the word, wherein the word needing to be corrected and the word used for correcting the word needing to be corrected are in a word-in-word relationship; a searching module, configured to search, by using a pronunciation confusion matrix, candidate words for correcting the word to be corrected from the word to be corrected, where the pronunciation confusion matrix includes a probability that each pronunciation is recognized as another pronunciation; and the error correction module is used for correcting the word needing to be corrected by using the candidate word.

In a third aspect, the present disclosure provides a computer readable medium having stored thereon a computer program which, when executed by a processing apparatus, performs the steps of the method of the first aspect of the present disclosure.

In a fourth aspect, the present disclosure provides an electronic device comprising: a storage device having a computer program stored thereon; processing means for executing the computer program in the storage means to implement the steps of the method of the first aspect of the present disclosure.

By adopting the technical scheme, whether the text after voice recognition belongs to the text of the characters in the words is checked on the basis of the expression characteristics of the text of the characters in the words, then if the text after voice recognition belongs to the text of the characters in the words, the characters needing to be corrected and the words needing to be corrected are extracted from the text after voice recognition, then candidate characters used for correcting the characters needing to be corrected are searched from the words needing to be corrected by utilizing a pronunciation confusion matrix, and finally the characters needing to be corrected are corrected by utilizing the candidate characters, so that the characters which are wrong in voice recognition can be corrected by utilizing the correct words in the text of the characters in the words after voice recognition, the sentence accuracy of voice recognition can be greatly improved, the characters in the words in the recognition result are corrected, and the user experience of voice recognition is improved.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale. In the drawings:

fig. 1 is a flowchart of a method of correcting text after speech recognition according to an embodiment of the present disclosure.

Fig. 2 is a schematic block diagram of an apparatus for correcting text after speech recognition according to an embodiment of the present disclosure.

Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

Fig. 1 is a flowchart of a method of correcting text after speech recognition according to an embodiment of the present disclosure. As shown in fig. 1, the method includes the following steps S11 to S14.

In step S11, it is checked whether the text after speech recognition belongs to the text of the word in question based on the expression characteristics of the text of the word in question.

The in-word text generally has the following expression features, i.e., B … "of … a, for example, where a represents a word such as idioms, poems, etc., and B represents the word in a. For example, "what words can be grouped in a rooster that asks about love", "how yellowbirds from two yellowbird song willows", "what meaning is considered in three-quarter cottage", "what is the number in nine-quarter cottage", "what is the intertwined pinyin", "what is the correct stroke, and" how to wake up "are all word texts in words, and these words are words in word texts," love house "," yellowbird song willow "," three-quarter cottage "," nine-quarter cottage "," intertwine "," correct "," wake up ", and the like," house "," yellowbird "," look "," number "," tangle "," straight ", and the like are words in the word texts in words.

And if the text after the voice recognition accords with the expression characteristics of the word text in the word, the text after the voice recognition is considered to belong to the word text in the word, otherwise, the text is considered not to belong to the word text in the word. If the text is not considered to belong to the word text in the word, the subsequent steps are not executed, and other text after speech recognition is continuously checked.

In speech recognition, usually, the words in the text of the word in the word are correctly recognized, and the words in the text of the word in the word as described above may be incorrectly recognized. For example, "what word can be grouped in a cottage asking for love," may be recognized as "what word can be grouped in a cottage asking for love," how the birds of the two yellowbird cuiliums write "may be recognized as" how the birds of the two yellowbird cuiliums leave. Therefore, it is necessary to correct the text of the word in the speech-recognized word so that the result of the speech recognition becomes more accurate and reasonable.

In step S12, if the text after the voice recognition belongs to the word-in-word text, a word that needs to be corrected and a word for correcting the word that needs to be corrected are extracted from the text after the voice recognition, where the word that needs to be corrected and the word for correcting the word that needs to be corrected have a word-in-word relationship.

In the step, extraction is mainly performed based on the expression characteristics of the text of the words in the words. For example, the boundary division may be performed on the words in the text after the speech recognition based on the expression characteristics of the text of the words in the words; then, based on the expression characteristics of the word text in the words, the words needing to be corrected and the words used for correcting the words needing to be corrected are extracted from the words after the boundary division.

The generic word-in-word "B … of … A" is still exemplified above. When boundary division is performed, the word text in the word can be divided into 5 parts, that is: the part before a, the part "a", "d", the part after B, B; b is a word that is likely to be misrecognized by speech recognition, and A is a candidate word for correcting B. Taking "what words can be grouped in the set asking for love, as an example," the part before a is "asking," a is "love, B is" set, "and the part after B is" what words can be grouped. In the extraction, a and B are extracted from the divided 5 parts.

In addition, based on the length characteristics of chinese words, the maximum number of words that need to be corrected is two, and the maximum number of words that need to be corrected is 7.

In step S13, candidate words for correcting the word to be corrected are found from the words to be corrected using a pronunciation confusion matrix including probabilities that each pronunciation is recognized as another pronunciation.

The pronunciation confusion matrix may be obtained as follows.

Firstly, obtaining the probability distribution y ∈ R of each frame of each sentence by utilizing an acoustic model and a labeled text^vWhere v is the size of the pronunciation dictionary, y is the index of the maximum probability idx, the list of pronunciation dictionaries (e.g., "ai 1", "ai 2", etc., where the numbers indicate pitch) is tokens, and y is tokens [ idx [ ]]Probability distribution of the recognition result of this word. The acoustic model refers to a model which can return a pronunciation sequence corresponding to an input audio characteristic, and the label text refers to a word corresponding to the audio.

Then, by means of the average value of y in a plurality of test sets, a probability matrix, namely a pronunciation confusion matrix, can be obtained for each pronunciation to be recognized as other pronunciations. By using the pronunciation confusion matrix in the text error correction process after the voice recognition, the pronunciation information contained in the acquired pronunciation similarity can be more complete, and the voice recognition error correction effect is better.

For example, assume that the pronunciation dictionary has 3 pronunciations, "ai 1", "ai 2", and "ai 3", respectively, resulting in a pronunciation confusion matrix as shown in table 1 below. It can be seen from the pronunciation confusion matrix that the probability of "ai 1" being read as "ai 1" is 0.8, the probability of "ai 1" being read as "ai 2" is 0.15, and the probability of "ai 1" being read as "ai 3" is 0.05.

	ai1	ai2	ai3
				ai1	0.8	0.15	0.05
ai2	0.2	0.75	0.05
				ai3	0.15	0.05	0.8

TABLE 1

The step S13 can be implemented in various ways, and one way of implementation may be: firstly, acquiring the similarity of the pinyin of each character in the words corrected by the characters to be corrected and the pinyin of the characters to be corrected by using a pronunciation confusion matrix; then, if the similarity is greater than a preset threshold, it is determined that the word is a candidate word for error correction of the word that needs to be error corrected.

In one embodiment, in the case that the word to be corrected is a word, the pronunciation confusion matrix may be used to obtain the similarity between the pinyin of each word in the word corrected by the word to be corrected and the pinyin of the word to be corrected.

For example, taking the case where the text after the speech recognition is "how to wake up" as an example, after the word to be corrected is "yes" and the word to be corrected is "awake" are extracted in step S12, the similarity between the pinyin of each word in "awake", that is, "sense" and "awake", and the pinyin of the word to be corrected "no" is obtained in step S13 using the pronunciation confusion matrix.

In another embodiment, in the case that the word to be corrected is two words, the pronunciation confusion matrix may be used to obtain the similarity between the pinyin of the two words selected in sequence from the first word of the words to be corrected and the pinyin of the two words of the word to be corrected.

For example, taking the example that the text after the voice recognition is "how to write the yellow calendars of two yellowbird cuiliums", after extracting that the word to be corrected is "yellow calendars" and the word to be corrected is "two yellowbird cuiliums" in step S12, in step S13, firstly, the pronunciation confusion matrix is used to obtain the pinyin similarity between "two" of the "two yellowbird cuiliums" and the word to be corrected "yellow calendars", then the pronunciation confusion matrix is used to obtain the pinyin similarity between "yellow only" of the "two yellowbird cuiliums" and the word to be corrected "yellow calendars", then the pronunciation confusion matrix is used to obtain the pinyin similarity between "yellow bird" of the "two yellowbird cui" and the word to be corrected "yellow calendars", and then the pronunciation confusion matrix is used to obtain the error correction similarity between "yellow bird of the" cuims "of the" cuili "and the word to be corrected" yellow calendars "of the two yellowbird cuits",cui "cui" cui is used to obtain the pronunciation confusion matrix, and then, obtaining the pinyin similarity between the cuisine of the two yellowbird cuisine willows and the character yellow calendar needing to be corrected by utilizing the pronunciation confusion matrix, and then obtaining the pinyin similarity between the cuisine of the two yellowbird cuisine willows and the character yellow calendar needing to be corrected by utilizing the pronunciation confusion matrix.

In addition, in the case where the word to be corrected is one word or two words, there may be a case where the word to be corrected is a polyphonic word, that is, there are a plurality of pronunciations. In the case of occurrence of polyphone characters, it is necessary to obtain the similarity between the pinyin of each character in the word corrected for the character to be corrected and each pronunciation of the character to be corrected.

Taking the example that the text after the speech recognition is "how to write with continuous feeling", since "the feeling" has a plurality of pronunciations, for example, "ju é" can be read, and "ji" o "can also be read, when the similarity is obtained, the similarity between each pronunciation of" the feeling "and the pinyin of each character in" continuous "needs to be obtained.

Further, taking the example that the text after the speech recognition is "how to write the Han of the Han Ganling". The "Han" has a plurality of pronunciations, for example, "Da h a n" can be read, and "Da h a n" can also be read, so that the similarity between each pronunciation of the "Han" and the pinyin of every two consecutive characters in the "Han Ganling" needs to be obtained when the similarity is obtained.

In step S14, the word that needs to be error corrected is error corrected using the candidate word.

That is, in this step, the word to be error-corrected is error-corrected by selecting the candidate word having the greatest similarity from among the candidate words. Still taking the example of "two yellowbird cuilius" as an example, assuming that the pinyin similarity between "yellowbird" and the word "yellowcalendar" that needs to be corrected is the largest as obtained in step S13, the word "yellowbird" that needs to be corrected is corrected to "yellowbird" in step S14. Therefore, after the post-processing, the text after the voice recognition is corrected from "how the yellows of the two yellowbird cuilius are written" to "how the yellowbirds of the two yellowbird cuilius are written".

Fig. 2 is a schematic block diagram of an apparatus for correcting text after speech recognition according to an embodiment of the present disclosure. As shown in fig. 2, the apparatus includes: the checking module 21 is configured to check whether the text after the voice recognition belongs to the text of the word in the word based on the expression characteristics of the text of the word in the word; an extracting module 22, configured to extract, if the text after the speech recognition belongs to a word-in-word text, a word that needs to be corrected and a word that is used to correct the word that needs to be corrected from the text after the speech recognition, where a relationship between the word that needs to be corrected and the word that is used to correct the word that needs to be corrected is a word-in-word relationship; a searching module 23, configured to search candidate words for correcting the word to be corrected from the words to be corrected by using a pronunciation confusion matrix, where the pronunciation confusion matrix includes probabilities that each pronunciation is recognized as another pronunciation; and an error correction module 24, configured to perform error correction on the word to be error corrected by using the candidate word.

Optionally, the checking module 21 is further configured to: checking whether the text after the voice recognition meets the expression characteristics of 'B of A', wherein A is a word and B is a character in A; and if the text after the voice recognition meets the expression characteristic of 'B of A', the text after the voice recognition belongs to a word-in-word text.

Optionally, the extraction module 22 comprises: the boundary dividing submodule is used for carrying out boundary division on words in the text after the voice recognition based on the expression characteristics of the word text in the words; and the extraction submodule is used for extracting the words needing to be corrected and the words for correcting the words needing to be corrected from the words after the boundary division based on the expression characteristics of the word texts in the words.

Alternatively, the word to be corrected has a maximum of two words, and the word to be corrected has a maximum of 7 words.

Optionally, the finding module 23 includes: the obtaining submodule is used for obtaining the similarity of the pinyin of each character in the words corrected by the characters needing error correction and the pinyin of the characters needing error correction by utilizing the pronunciation confusion matrix; and the determining submodule is used for determining that the word is a candidate word for correcting the error of the word needing to be corrected if the similarity is greater than a preset threshold.

Optionally, the obtaining sub-module is configured to: and under the condition that the character needing to be corrected is a character, acquiring the similarity of the pinyin of each character in the word corrected by the character needing to be corrected and the pinyin of the character needing to be corrected by using the pronunciation confusion matrix.

Optionally, the obtaining sub-module is configured to: and under the condition that the characters needing to be corrected are two characters, acquiring the similarity between the pinyin of the two characters selected in sequence from the initial character in the words needing to be corrected and the pinyin of the two characters of the characters needing to be corrected by utilizing the pronunciation confusion matrix.

Optionally, the obtaining sub-module is further configured to: if the character to be corrected has a plurality of pronunciations, acquiring the similarity between the pinyin of each character in the word corrected by the character to be corrected and each pronunciation of the character to be corrected.

Optionally, the error correction module 24 is further configured to: and selecting the candidate word with the maximum similarity from the candidate words to correct the error of the word needing to be corrected.

Referring now to FIG. 3, a block diagram of an electronic device 600 suitable for use in implementing embodiments of the present disclosure is shown. The terminal device in the embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. The electronic device shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 3, electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of the embodiments of the present disclosure.

It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: checking whether the text after voice recognition belongs to the text of the characters in the words or not based on the expression characteristics of the text of the characters in the words; if the text after the voice recognition belongs to a word text in words, extracting words needing to be corrected and words used for correcting the words needing to be corrected from the text after the voice recognition, wherein the words needing to be corrected and the words used for correcting the words needing to be corrected are in a word-in-word relationship; searching candidate words for correcting the word needing to be corrected from the words for correcting the word needing to be corrected by using a pronunciation confusion matrix, wherein the pronunciation confusion matrix comprises the probability that each pronunciation is recognized as other pronunciations; and correcting the word needing to be corrected by using the candidate word.

Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present disclosure may be implemented by software or hardware. Wherein the name of a module in some cases does not constitute a limitation on the module itself.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Example 1 provides a method of correcting a text after speech recognition, including: checking whether the text after voice recognition belongs to the text of the characters in the words or not based on the expression characteristics of the text of the characters in the words; if the text after the voice recognition belongs to a word text in words, extracting words needing to be corrected and words used for correcting the words needing to be corrected from the text after the voice recognition, wherein the words needing to be corrected and the words used for correcting the words needing to be corrected are in a word-in-word relationship; searching candidate words for correcting the word needing to be corrected from the words for correcting the word needing to be corrected by using a pronunciation confusion matrix, wherein the pronunciation confusion matrix comprises the probability that each pronunciation is recognized as other pronunciations; and correcting the word needing to be corrected by using the candidate word.

Example 2 provides the method of example 1, wherein the checking whether the text after the speech recognition belongs to the text of the word in word based on the expression characteristics of the text of the word in word comprises: checking whether the text after the voice recognition meets the expression characteristics of 'B of A', wherein A is a word and B is a character in A; and if the text after the voice recognition meets the expression characteristic of 'B of A', the text after the voice recognition belongs to a word-in-word text.

Example 3 provides the method of example 1, wherein the extracting, from the speech-recognized text, the word that needs to be corrected and the word for correcting the word that needs to be corrected includes: carrying out boundary division on words in the text after the voice recognition based on the expression characteristics of the word text in the words; and extracting the words needing to be corrected and the words for correcting the words needing to be corrected from the words after the boundary division based on the expression characteristics of the word texts in the words.

Example 4 provides the method of example 1, wherein the finding, using a pronunciation confusion matrix, a candidate word for correcting the word requiring error correction from the words requiring error correction includes: acquiring the similarity between the pinyin of each character in the words corrected by the characters needing to be corrected and the pinyin of the characters needing to be corrected by utilizing the pronunciation confusion matrix; and if the similarity is larger than a preset threshold, determining that the word is a candidate word for correcting the error of the word needing to be corrected.

Example 5 provides the method of example 4, wherein the obtaining, using the pronunciation confusion matrix, a similarity between a pinyin of each word of the words to be corrected and a pinyin of the words to be corrected includes: and under the condition that the character needing to be corrected is a character, acquiring the similarity between the pinyin of each character in the words which are corrected by the character needing to be corrected and the pinyin of the character needing to be corrected by using the pronunciation confusion matrix.

Example 6 provides the method of example 4, wherein the obtaining, using the pronunciation confusion matrix, a similarity between a pinyin of each word of the words to be corrected and a pinyin of the words to be corrected includes: and under the condition that the characters needing error correction are two characters, acquiring the similarity between the pinyin of the two characters selected in sequence from the initial character in the words correcting the characters needing error correction and the pinyin of the two characters of the characters needing error correction by using the pronunciation confusion matrix.

Example 7 provides the method of example 5 or 6, wherein, if the word to be corrected has a plurality of pronunciations, a degree of similarity between a pinyin of each of the words to be corrected and each pronunciations of the word to be corrected is obtained.

Example 8 provides the method of example 1, wherein the error correcting the word to be error corrected using the candidate word includes: and selecting the candidate word with the maximum similarity from the candidate words to correct the error of the word needing to be corrected.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims. With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A method for correcting errors of a text after speech recognition, comprising:

checking whether the text after voice recognition belongs to the text of the characters in the words or not based on the expression characteristics of the text of the characters in the words;

if the text after the voice recognition belongs to a word text in words, extracting words needing to be corrected and words used for correcting the words needing to be corrected from the text after the voice recognition, wherein the words needing to be corrected and the words used for correcting the words needing to be corrected are in a word-in-word relationship;

searching candidate words for correcting the word needing to be corrected from the words for correcting the word needing to be corrected by using a pronunciation confusion matrix, wherein the pronunciation confusion matrix comprises the probability that each pronunciation is recognized as other pronunciations;

and correcting the word needing to be corrected by using the candidate word.

2. The method of claim 1, wherein checking whether the text after speech recognition belongs to the text of the word in the word based on the expression characteristics of the text of the word in the word comprises:

checking whether the text after the voice recognition meets the expression characteristics of 'B of A', wherein A is a word and B is a character in A;

and if the text after the voice recognition meets the expression characteristic of 'B of A', the text after the voice recognition belongs to a word-in-word text.

3. The method according to claim 1, wherein the extracting words to be corrected and words for correcting the words to be corrected from the text after the speech recognition comprises:

carrying out boundary division on words in the text after the voice recognition based on the expression characteristics of the word text in the words;

and extracting the words needing to be corrected and the words for correcting the words needing to be corrected from the words after the boundary division based on the expression characteristics of the word texts in the words.

4. The method according to claim 1, wherein the finding, by using a pronunciation confusion matrix, a candidate word for correcting the word to be corrected from the word to be corrected comprises:

acquiring the similarity between the pinyin of each character in the words corrected by the characters needing to be corrected and the pinyin of the characters needing to be corrected by utilizing the pronunciation confusion matrix;

and if the similarity is larger than a preset threshold, determining that the word is a candidate word for correcting the error of the word needing to be corrected.

5. The method according to claim 4, wherein the obtaining the similarity between the pinyin of each word in the word corrected by the word to be corrected and the pinyin of the word to be corrected by using the pronunciation confusion matrix comprises:

and under the condition that the character needing to be corrected is a character, acquiring the similarity between the pinyin of each character in the words which are corrected by the character needing to be corrected and the pinyin of the character needing to be corrected by using the pronunciation confusion matrix.

6. The method according to claim 4, wherein the obtaining the similarity between the pinyin of each word in the word corrected by the word to be corrected and the pinyin of the word to be corrected by using the pronunciation confusion matrix comprises:

and under the condition that the characters needing error correction are two characters, acquiring the similarity between the pinyin of the two characters selected in sequence from the initial character in the words correcting the characters needing error correction and the pinyin of the two characters of the characters needing error correction by using the pronunciation confusion matrix.

7. The method according to claim 5 or 6, wherein if the word to be corrected has a plurality of pronunciations, the similarity between the pinyin of each word in the word to be corrected and each pronunciation of the word to be corrected is obtained.

8. The method of claim 1, wherein said error correcting the word to be error corrected using the candidate word comprises:

and selecting the candidate word with the maximum similarity from the candidate words to correct the error of the word needing to be corrected.

9. An apparatus for correcting a text after speech recognition, comprising:

the checking module is used for checking whether the text after the voice recognition belongs to the text of the characters in the words or not based on the expression characteristics of the text of the characters in the words;

the extraction module is used for extracting a word needing to be corrected and a word used for correcting the word needing to be corrected from the text after the voice recognition if the text after the voice recognition belongs to a word text in the word, wherein the word needing to be corrected and the word used for correcting the word needing to be corrected are in a word-in-word relationship;

a searching module, configured to search, by using a pronunciation confusion matrix, candidate words for correcting the word to be corrected from the word to be corrected, where the pronunciation confusion matrix includes a probability that each pronunciation is recognized as another pronunciation;

and the error correction module is used for correcting the word needing to be corrected by using the candidate word.

10. A computer-readable medium, on which a computer program is stored, characterized in that the program, when being executed by processing means, carries out the steps of the method of any one of claims 1 to 8.

11. An electronic device, comprising:

a storage device having a computer program stored thereon;

processing means for executing the computer program in the storage means to carry out the steps of the method according to any one of claims 1 to 8.