CN108389584A - Sound analysis method and device - Google Patents
Sound analysis method and device Download PDFInfo
- Publication number
- CN108389584A CN108389584A CN201810096118.7A CN201810096118A CN108389584A CN 108389584 A CN108389584 A CN 108389584A CN 201810096118 A CN201810096118 A CN 201810096118A CN 108389584 A CN108389584 A CN 108389584A
- Authority
- CN
- China
- Prior art keywords
- audio
- frequency information
- sound
- categories
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 claims description 21
- 238000009826 distribution Methods 0.000 claims description 20
- 230000002123 temporal effect Effects 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 11
- 238000000926 separation method Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000004807 localization Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/638—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0272—Voice signal separating
- G10L21/028—Voice signal separating using properties of sound source
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Stereophonic System (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The present invention provides a kind of sound analysis method and devices, obtain audio-frequency information to be analyzed, include the audio-frequency information of multiple and different audio categories in the audio-frequency information to be analyzed；Determine the audio categories of each audio-frequency information；According to the audio categories, the characteristic information of the audio-frequency information is obtained；The characteristic information includes source of sound distance, decibel value；According to the source of sound distance of the audio-frequency information, the audio-frequency information is distributed in the layering of sound map, wherein the sound map is layered according to distance；The sound analysis method and device provided in the present invention, the sound in sound map according to source of sound apart from Layering manifestation separate sources is intuitive to show, and shows abundant in content.
Description
Technical field
The present invention relates to voice recognition technology field, more particularly to a kind of sound analysis method and device.
Background technology
Video monitoring is the important information source that current every profession and trade carries out safety management, dispute processing, however video monitoring
It will appear blind sector, having the personnel of bad motivation that can deliberately hide has the place of monitoring to implement illegal activities, to thing truth
Discovery cause very big puzzlement.
And the propagation of sound limits almost without blind area, small-scale block will not cause prodigious masking.Therefore, right
The analysis of sound will play the role of prodigious information supplement.
Sound map common at present generally refers to city or noise region map, the size of noise everywhere is used different
Visual effect is presented on map, intuitive that noise profile situation is presented.But the information that this sound map is presented is less, can only
The decibel value of simple performance sound, is generally only used for judging the distribution of noise, sound more can not be analyzed and be answered
With.
Invention content
The main object of the present invention is to provide a kind of sound analysis method, by the audio distribution of different distance in sound map
In.
The present invention proposes a kind of sound analysis method, includes the following steps：
Audio-frequency information to be analyzed is obtained, includes the audio letter of multiple and different audio categories in the audio-frequency information to be analyzed
Breath；
Determine the audio categories of each audio-frequency information；
According to the audio categories, the characteristic information of the audio-frequency information is obtained；The characteristic information include source of sound distance,
Decibel value；
According to the source of sound distance of the audio-frequency information, the audio-frequency information is distributed in the layering of sound map, wherein
The sound map is layered according to distance.
Further, the audio-frequency information is distributed in sound map by the source of sound distance according to the audio-frequency information
Layering in step after, including：
When receiving preset trigger signal in the layering, sound source is carried out to the audio-frequency information in layering and is gone
It makes an uproar, audio optimization processing, and the audio-frequency information after playback process.
Further, the audio-frequency information is distributed in sound map by the source of sound distance according to the audio-frequency information
Layering in step after, including：
If in layering there are many distributions when the audio-frequency information of audio categories, by the corresponding audio of multiple audio categories
Information carries out separation and shows.
Further, the determination each the audio categories of the audio-frequency information the step of include：
It is compared with the feature audio to prestore in database, with the audio categories of the determination audio-frequency information.
Further, after the step of acquisition audio-frequency information to be analyzed, further include：
Obtain source place and the temporal information of the audio-frequency information；
According to the source place and temporal information, the first audio categories are selected；
The determination each the audio categories of the audio-frequency information the step of include then：
By the frequency of the first audio categories character pair audio to prestore in the frequency of the audio-frequency information and database into
Row comparison, and calculate the similarity of the audio-frequency information and feature audio；
When similarity reaches preset value, the audio categories of the audio-frequency information are determined.
The present invention also provides a kind of sound analysis devices, including：
First acquisition unit, include for obtaining audio-frequency information to be analyzed, in the audio-frequency information to be analyzed it is multiple not
With the audio-frequency information of audio categories；
Determination unit, the audio categories for determining the audio-frequency information；
Second acquisition unit, for according to the audio categories, obtaining the characteristic information of the audio-frequency information；The feature
Information includes source of sound distance, decibel value；
The audio-frequency information is distributed in sound map by distribution unit for the source of sound distance according to the audio-frequency information
Layering in, wherein the sound map is layered according to distance.
Further, further include：
Broadcast unit when for receiving preset trigger signal in the layering, is believed the audio in layering
Breath carries out sound source denoising, audio optimization processing, and the audio-frequency information after playback process.
Further, further include：
Separative element, if when for being distributed the audio-frequency information there are many audio categories in being layered, by multiple audio categories
Corresponding audio-frequency information carries out separation and shows.
Further, the determination unit is specifically used for：
It is compared with the feature audio to prestore in database, with the audio categories of the determination audio-frequency information.
Further, further include：
Third acquiring unit, the source place for obtaining the audio-frequency information and temporal information；
Selecting unit, for according to the source place and temporal information, selecting the first audio categories；
The determination unit includes then：
Contrast subunit, for the frequency of the audio-frequency information is corresponding with the first audio categories to prestore in database special
The frequency of sign audio is compared, and calculates the similarity of the audio-frequency information and feature audio；
Determination subelement, for when the similarity reaches preset value, determining the audio categories of the audio-frequency information.
The sound analysis method and device provided in the present invention, has the advantages that：
The sound analysis method and device provided in the present invention obtains audio-frequency information to be analyzed, the audio letter to be analyzed
It include the audio-frequency information of multiple and different audio categories in breath；Determine the audio categories of each audio-frequency information；According to described
Audio categories obtain the characteristic information of the audio-frequency information；The characteristic information includes source of sound distance, decibel value；According to described
The source of sound distance of audio-frequency information, the audio-frequency information is distributed in the layering of sound map, wherein the sound map according to
Distance is layered；Sound in sound map according to source of sound apart from Layering manifestation separate sources, it is intuitive to show, and in display
Hold abundant.
Description of the drawings
Fig. 1 is sound analysis method step schematic diagram in one embodiment of the invention；
Fig. 2 is sound analysis method step schematic diagram in another embodiment of the present invention；
Fig. 3 is sound analysis method step schematic diagram in further embodiment of this invention；
Fig. 4 is sound analysis device structure diagram in one embodiment of the invention；
Fig. 5 is sound analysis device structure diagram in another embodiment of the present invention；
Fig. 6 is determination unit structure diagram in one embodiment of the invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific implementation mode
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singulative " one " used herein, " one
It is a ", " described " " above-mentioned " and "the" may also comprise plural form.It is to be further understood that making in the specification of the present invention
Wording " comprising " refers to that there are the feature, integer, step, operation, element, unit, module and/or components, but simultaneously
Do not preclude the presence or addition of other one or more features, integer, step, operation, element, unit, module, component and/or it
Group.It should be understood that when we say that an element is " connected " or " coupled " to another element, it can be directly connected to or couple
To other elements, or there may also be intermediary elements.In addition, " connection " used herein or " coupling " may include wirelessly connecting
It connects or wirelessly couples.Wording "and/or" used herein includes the whole or any of one or more associated list items
Unit and all combination.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific terminology), there is meaning identical with the general understanding of the those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have in the context of the prior art
The consistent meaning of meaning, and unless by specific definitions as here, the meaning of idealization or too formal otherwise will not be used
To explain.
Referring to Fig.1, it is the sound analysis method step schematic diagram in one embodiment of the invention.
A kind of sound analysis method is proposed in one embodiment of the invention, is applied to intelligent terminal, is included the following steps：
Step S1 obtains audio-frequency information to be analyzed, includes multiple and different audio categories in the audio-frequency information to be analyzed
Audio-frequency information；
Step S2 determines the audio categories of each audio-frequency information；
Step S3 obtains the characteristic information of the audio-frequency information according to the audio categories；The characteristic information includes sound
Source distance, decibel value；
The audio-frequency information is distributed in the layering of sound map by step S4 according to the source of sound distance of the audio-frequency information
It is interior, wherein the sound map is layered according to distance.
Only show that the decibel value of various sound, the information of display are smaller on usual sound map.In the present embodiment, it obtains
To a section audio information, which includes the audio-frequency information there are many audio categories.Audio categories in the present embodiment
Refer to that the audio categories delimited according to the sound source of audio, such as sound, sound of the wind, tweedle and pedestrian that vehicle to run is sent out are said
The sound of words is different audio categories.Above-mentioned audio-frequency information to be analyzed is analyzed, is determined wherein included each
The audio categories of audio-frequency information.
It is understood that some audios may not have corresponding source of sound distance, such as sound of the wind, thunder and lightning sound etc., this reality
It applies in example and sets the source of sound distance of this class audio frequency to infinity.Therefore, the difference of audio categories, the source of sound distance got is not
Together.In the present embodiment, according to the difference of audio categories, its source of sound distance is determined according to different rules.Source of sound distance belongs to sound
One characteristic information of frequency information, this feature information can also include audio categories, decibel value, loudness, clarity etc..Specifically
Ground can determine the source of sound distance of audio-frequency information by auditory localization.
Finally, source of sound distance is provided with multiple layerings in sound map in the present embodiment, each layering represents difference
The audio-frequency information of source of sound distance, by the above-mentioned audio-frequency information for getting source of sound distance according to corresponding source of sound range distribution in sound
In map；Meanwhile also by the characteristic informations such as the corresponding audio categories of audio-frequency information, decibel value include in sound map, so as to
It can intuitively check the relevant information of audio.
It can also include the following steps after above-mentioned steps S2：
According to audio categories, handled according to predetermined manner.In the present embodiment, for the audio of different audio categories
Information takes different processing routines to be handled；Processing routine mainly goes hot-tempered, audio optimization including auditory localization, sound source.
For example, in the present embodiment, being preset with the mode handled the audio-frequency information of a variety of different audio categories：
(1) voice：Judge voice number of sources, carries out sound bearing and Distance Judgment respectively, and by each voice clear
Presentation is optimized in terms of degree, sound intensity.
(2) traffic sound：Traffic sound includes mainly land, sea and sky three classes；It is each including automobile, train, ship, aircraft etc.
Class traffic noise and wheel and ground/rail grating, engine sound, exhaust sound, whistle sound etc..Judge for traffic sound
Traffic sound type in audio-frequency information, and presented after optimizing.
(3) building site sound：Include the running noises of the construction equipments such as piling machine, bull-dozer.Mainly judge sound for building site sound
Source distance and audio categories.
(4) musical sound：The source of musical sound is usually that businessman or personal broadcasting loudspeaker generate under conventional environment.For music
Sound mainly judges source of sound distance and audio categories.
(5) natural phonation：Including wind and rain sound caused by weather, thunder and lightning sound, flow sound etc..When the sound for judging a certain characteristic frequency
When sound is natural phonation, without judging sound source distance, it is directly displayed as the sound of unlimited distance.
To the processing procedure of audio-frequency information can be before audio-frequency information is distributed in the layering of sound map, can also
It is after distribution；If processing procedure before distribution, when receiving preset trigger signal in the layering, is then directly broadcast
Put the audio-frequency information in the layering；If processing procedure is after distribution, with reference to Fig. 2, in one embodiment, described
According to the source of sound distance of the audio-frequency information, the audio-frequency information is distributed in after the step S4 in the layering of sound map, is wrapped
It includes：
Step S5 when receiving preset trigger signal in the layering, carries out the audio-frequency information in layering
Sound source denoising, audio optimization processing, and the audio-frequency information after playback process.
After by audio-frequency information layer distributed on sound map, user operates intelligent terminal, pre- to trigger
If trigger signal, when intelligent terminal receives above-mentioned trigger signal by region residing for layering, then play automatically in the layering
The audio-frequency information of distribution；Above-mentioned preset trigger signal could be provided as clicking triggering, or double-clicking triggering etc..Preferably,
Before playing above-mentioned audio-frequency information, above-mentioned audio-frequency information is filtered, denoising, audio optimization processing.
In another embodiment, the audio-frequency information is distributed in sound by the source of sound distance according to the audio-frequency information
After step S4 in the layering of sound map, including：
Step S6, if in layering there are many distributions when the audio-frequency information of audio categories, multiple audio categories are right respectively
The audio-frequency information answered carries out separation and shows.Distinguished convenient for the audio-frequency information to same audio source distance, when its be distributed in it is same
When layering, then the corresponding audio-frequency information of multiple audio categories is subjected to separation and shown, can use different lines face
Color distinguishes.
Specifically, in one embodiment, the step S2 of each audio categories of the audio-frequency information of the determination includes：
It is compared with the feature audio to prestore in database, with the audio categories of the determination audio-frequency information.
In the present embodiment, such as voice, traffic sound, building site voice music, natural phonation are prestored in the database of system
Etc. all kinds of feature audios, it needs to be determined that audio-frequency information to be analyzed audio categories when, only need to by its with prestore in database
Feature audio is compared, and judges whether similar, if similarity reaches preset value, judges it for the corresponding sound of this feature audio
Frequency classification.
With reference to Fig. 3, in another embodiment, after the step S1 for obtaining audio-frequency information to be analyzed, further include：
Step S1a obtains source place and the temporal information of the audio-frequency information；
Step S1b selects the first audio categories according to the source place and temporal information；
The step S2 of each audio categories of the audio-frequency information of the determination includes then：
Step S2a, the first audio categories character pair audio that will be prestored in the frequency of the audio-frequency information and database
Frequency compared, and calculate the similarity of the audio-frequency information and feature audio；
Step S2b determines the audio categories of the audio-frequency information when similarity reaches preset value.
If audio-frequency information and pre-stored characteristics audio in database are compared one by one, calculation amount is larger, in this implementation
In example, in order to reduce calculation amount, geography information (source place when acquisition audio is got from audio-frequency information to be analyzed first
Point) and temporal information, according to source place and temporal information, selection points out the main audio of period appearance on the ground
Classification (i.e. the first audio categories)；Such as place is when being located at urban traffic road, audio-frequency information should be mainly traffic, secondly
It, then can be using traffic sound as the first audio categories for voice.Then, it will prestore in the frequency of the audio-frequency information and database
The frequency of the first audio categories character pair audio compared, and it is similar to feature audio to obtain the audio-frequency information
Degree, when similarity reaches preset value, determines the audio categories of the audio-frequency information.In this way, calculation amount can be reduced largely, carry
Rise analyze speed.
In conclusion for the sound analysis method provided in the embodiment of the present invention, audio-frequency information to be analyzed is obtained, it is described to wait for
It include the audio-frequency information of multiple and different audio categories in analysis audio-frequency information；Determine the audio class of each audio-frequency information
Not；According to the audio categories, the characteristic information of the audio-frequency information is obtained；The characteristic information includes source of sound distance, decibel
Value；According to the source of sound distance of the audio-frequency information, the audio-frequency information is distributed in the layering of sound map, wherein the sound
Sound map is layered according to distance；Sound in sound map according to source of sound apart from Layering manifestation separate sources, it is intuitive aobvious
Show, and shows abundant in content.
With reference to Fig. 4, a kind of sound analysis device is additionally provided in one embodiment of the invention, is applied to intelligent terminal, including：
First acquisition unit 10 includes multiple in the audio-frequency information to be analyzed for obtaining audio-frequency information to be analyzed
The audio-frequency information of different audio categories；
Determination unit 20, the audio categories for determining the audio-frequency information；
Second acquisition unit 30, for according to the audio categories, obtaining the characteristic information of the audio-frequency information；The spy
Reference breath includes source of sound distance, decibel value；
Distribution unit 40, for the source of sound distance according to the audio-frequency information, with being distributed in sound by the audio-frequency information
In the layering of figure, wherein the sound map is layered according to distance.
Only show that the decibel value of various sound, the information of display are smaller on usual sound map.In the present embodiment, it obtains
To a section audio information, which includes the audio-frequency information there are many audio categories.Audio categories in the present embodiment
Refer to that the audio categories delimited according to the sound source of audio, such as sound, sound of the wind, tweedle and pedestrian that vehicle to run is sent out are said
The sound of words is different audio categories.Above-mentioned audio-frequency information to be analyzed is analyzed, determination unit 20 is determined wherein
Including each audio-frequency information audio categories.
It is understood that some audios may not have corresponding source of sound distance, such as sound of the wind, thunder and lightning sound etc., this reality
It applies in example and sets the source of sound distance of this class audio frequency to infinity.Therefore, the difference of audio categories, the source of sound distance got is not
Together.In the present embodiment, second acquisition unit 30 determines its source of sound distance according to the difference of audio categories according to different rules.
Source of sound distance belongs to a characteristic information of audio-frequency information, this feature information can also include audio categories, decibel value, loudness,
Clarity etc..Specifically, the source of sound distance of audio-frequency information can be determined by auditory localization.
Finally, source of sound distance is provided with multiple layerings in sound map in the present embodiment, each layering represents difference
The audio-frequency information of source of sound distance, distribution unit 40 is by the above-mentioned audio-frequency information for getting source of sound distance according to corresponding source of sound distance
It is distributed in sound map；Meanwhile also including in sound by characteristic informations such as the corresponding audio categories of audio-frequency information, decibel values
In figure, so as to intuitively check the relevant information of audio.
The above sound analytical equipment can also include：
Processing unit, for according to audio categories, being handled according to predetermined manner.In the present embodiment, for difference
The audio-frequency information of audio categories takes different processing routines to be handled；Processing routine is mainly gone including auditory localization, sound source
Hot-tempered, audio optimization.
For example, in the present embodiment, being preset with the mode handled the audio-frequency information of a variety of different audio categories：
(1) voice：Judge voice number of sources, carries out sound bearing and Distance Judgment respectively, and by each voice clear
Presentation is optimized in terms of degree, sound intensity.
(2) traffic sound：Traffic sound includes mainly land, sea and sky three classes；It is each including automobile, train, ship, aircraft etc.
Class traffic noise and wheel and ground/rail grating, engine sound, exhaust sound, whistle sound etc..Judge for traffic sound
Traffic sound type in audio-frequency information, and presented after optimizing.
(3) building site sound：Include the running noises of the construction equipments such as piling machine, bull-dozer.Mainly judge sound for building site sound
Source distance and audio categories.
(4) musical sound：The source of musical sound is usually that businessman or personal broadcasting loudspeaker generate under conventional environment.For music
Sound mainly judges source of sound distance and audio categories.
(5) natural phonation：Including wind and rain sound caused by weather, thunder and lightning sound, flow sound etc..When the sound for judging a certain characteristic frequency
When sound is natural phonation, without judging sound source distance, it is directly displayed as the sound of unlimited distance.
To the processing procedure of audio-frequency information can be before audio-frequency information is distributed in the layering of sound map, can also
It is after distribution；If processing procedure before distribution, when receiving preset trigger signal in the layering, is then directly broadcast
Put the audio-frequency information in the layering；If processing procedure after distribution, receives in layering default before being played
Trigger signal when, sound source denoising, audio optimization processing, then the institute after playback process are carried out to the audio-frequency information in layering
State audio-frequency information.
Specifically, further include in one embodiment with reference to Fig. 5：
Broadcast unit 50, when for receiving preset trigger signal in the layering, to the audio in layering
Information carries out sound source denoising, audio optimization processing, and the audio-frequency information after playback process.
After by audio-frequency information layer distributed on sound map, user operates intelligent terminal, pre- to trigger
If trigger signal, when intelligent terminal receives above-mentioned trigger signal by region residing for layering, then play automatically in the layering
The audio-frequency information of distribution；Above-mentioned preset trigger signal could be provided as clicking triggering, or double-clicking triggering etc..Preferably,
Before playing above-mentioned audio-frequency information, above-mentioned audio-frequency information is filtered, denoising, audio optimization processing.
In another embodiment, above-mentioned apparatus further includes：
Separative element, if when for being distributed the audio-frequency information there are many audio categories in being layered, by multiple audio categories
Corresponding audio-frequency information carries out separation and shows.It is distinguished convenient for the audio-frequency information to same audio source distance, when its distribution
In same layering, then the corresponding audio-frequency information of multiple audio categories is subjected to separation and shown, can be use it is different
Line color distinguishes.
Specifically, the determination unit 20 is specifically used for：
It is compared with the feature audio to prestore in database, with the audio categories of the determination audio-frequency information.
In the present embodiment, such as voice, traffic sound, building site voice music, natural phonation are prestored in the database of system
Etc. all kinds of feature audios, it needs to be determined that audio-frequency information to be analyzed audio categories when, only need to by its with prestore in database
Feature audio is compared, and judges whether similar, if similarity reaches preset value, judges it for the corresponding sound of this feature audio
Frequency classification.
Further, the above sound analytical equipment further includes：
Third acquiring unit, the source place for obtaining the audio-frequency information and temporal information；
Selecting unit, for according to the source place and temporal information, selecting the first audio categories；
With reference to Fig. 6, the determination unit 20 includes then：
Contrast subunit 201, the first audio categories pair for will prestore in the frequency of the audio-frequency information and database
It answers the frequency of feature audio to be compared, and calculates the similarity of the audio-frequency information and feature audio；
Determination subelement 202, for when the similarity reaches preset value, determining the audio class of the audio-frequency information
Not.
If audio-frequency information and pre-stored characteristics audio in database are compared one by one, calculation amount is larger, in this implementation
In example, in order to reduce calculation amount, third acquiring unit first gets ground when acquiring audio from audio-frequency information to be analyzed
Information (source place) and temporal information are managed, selecting unit is pointed out according to source place and temporal information, selection on the ground
The dominant audio class (i.e. the first audio categories) that the period occurs；Such as place is when being located at urban traffic road, audio
Information should be mainly traffic, secondly be voice, then can be using traffic sound as the first audio categories.Then, contrast subunit
201 carry out the frequency of the first audio categories character pair audio to prestore in the frequency of the audio-frequency information and database pair
Than, and the similarity of the audio-frequency information and feature audio is obtained, when similarity reaches preset value, determination subelement 202 is then
Determine the audio categories of the audio-frequency information.In this way, calculation amount can be reduced largely, analyze speed is promoted.
In conclusion for the sound analysis method and device that are provided in the embodiment of the present invention, audio-frequency information to be analyzed is obtained,
It include the audio-frequency information of multiple and different audio categories in the audio-frequency information to be analyzed；Determine the sound of each audio-frequency information
Frequency classification；According to the audio categories, the characteristic information of the audio-frequency information is obtained；The characteristic information include source of sound distance,
Decibel value；According to the source of sound distance of the audio-frequency information, the audio-frequency information is distributed in the layering of sound map, wherein institute
Sound map is stated to be layered according to distance；Sound in sound map according to source of sound apart from Layering manifestation separate sources, directly
Display is seen, and is shown abundant in content.
Those skilled in the art of the present technique be appreciated that can with computer program instructions come realize these structure charts and/or
The combination of each frame and these structure charts and/or the frame in block diagram and/or flow graph in block diagram and/or flow graph.This technology is led
Field technique personnel be appreciated that these computer program instructions can be supplied to all-purpose computer, special purpose computer or other
The processor of programmable data processing method is realized, to pass through the processing of computer or other programmable data processing methods
Device come execute structure chart and/or block diagram and/or flow graph disclosed by the invention frame or multiple frames in specify scheme.
Those skilled in the art of the present technique are appreciated that in the various operations crossed by discussion in the present invention, method, flow
Steps, measures, and schemes can be replaced, changed, combined or be deleted.Further, each with having been crossed by discussion in the present invention
Other steps, measures, and schemes in kind operation, method, flow may also be alternated, changed, rearranged, decomposed, combined or deleted.
Further, in the prior art to have and step, measure, the scheme in various operations, method, flow disclosed in the present invention
It may also be alternated, changed, rearranged, decomposed, combined or deleted.
The foregoing is merely the preferred embodiment of the present invention, are not intended to limit the scope of the invention, every utilization
Equivalent structure or equivalent flow shift made by description of the invention and accompanying drawing content is applied directly or indirectly in other correlations
Technical field, be included within the scope of the present invention.
Claims (10)
1. a kind of sound analysis method, which is characterized in that include the following steps：
Audio-frequency information to be analyzed is obtained, includes the audio-frequency information of multiple and different audio categories in the audio-frequency information to be analyzed；
Determine the audio categories of each audio-frequency information；
According to the audio categories, the characteristic information of the audio-frequency information is obtained；The characteristic information includes source of sound distance, decibel
Value；
According to the source of sound distance of the audio-frequency information, the audio-frequency information is distributed in the layering of sound map, wherein described
Sound map is layered according to distance.
2. sound analysis method according to claim 1, which is characterized in that the source of sound according to the audio-frequency information away from
From, the audio-frequency information is distributed in after the step in the layering of sound map, including：
When receiving preset trigger signal in the layering, sound source denoising, sound are carried out to the audio-frequency information in layering
Frequency optimization processing, and the audio-frequency information after playback process.
3. sound analysis method according to claim 1, which is characterized in that the source of sound according to the audio-frequency information away from
From, the audio-frequency information is distributed in after the step in the layering of sound map, including：
If in layering there are many distributions when the audio-frequency information of audio categories, by the corresponding audio-frequency information of multiple audio categories
Separation is carried out to show.
4. sound analysis method according to claim 1, which is characterized in that the sound of each audio-frequency information of the determination
The step of frequency classification includes：
It is compared with the feature audio to prestore in database, with the audio categories of the determination audio-frequency information.
5. sound analysis method according to claim 1, which is characterized in that the step of acquisition audio-frequency information to be analyzed
Later, further include：
Obtain source place and the temporal information of the audio-frequency information；
According to the source place and temporal information, the first audio categories are selected；
The determination each the audio categories of the audio-frequency information the step of include then：
The frequency of the first audio categories character pair audio to prestore in the frequency of the audio-frequency information and database is carried out pair
Than, and calculate the similarity of the audio-frequency information and feature audio；
When similarity reaches preset value, the audio categories of the audio-frequency information are determined.
6. a kind of sound analysis device, which is characterized in that including：
First acquisition unit includes multiple and different sounds in the audio-frequency information to be analyzed for obtaining audio-frequency information to be analyzed
The audio-frequency information of frequency classification；
Determination unit, the audio categories for determining the audio-frequency information；
Second acquisition unit, for according to the audio categories, obtaining the characteristic information of the audio-frequency information；The characteristic information
Including source of sound distance, decibel value；
The audio-frequency information is distributed in point of sound map by distribution unit for the source of sound distance according to the audio-frequency information
In layer, wherein the sound map is layered according to distance.
7. sound analysis device according to claim 6, which is characterized in that further include：
Broadcast unit, when for receiving preset trigger signal in the layering, to the audio-frequency information in layering into
The denoising of row sound source, audio optimization processing, and the audio-frequency information after playback process.
8. sound analysis device according to claim 6, which is characterized in that further include：
Separative element, if distinguishing multiple audio categories there are many when the audio-frequency information of audio categories for distribution in being layered
Corresponding audio-frequency information carries out separation and shows.
9. sound analysis device according to claim 6, which is characterized in that the determination unit is specifically used for：
It is compared with the feature audio to prestore in database, with the audio categories of the determination audio-frequency information.
10. sound analysis device according to claim 6, which is characterized in that further include：
Third acquiring unit, the source place for obtaining the audio-frequency information and temporal information；
Selecting unit, for according to the source place and temporal information, selecting the first audio categories；
The determination unit includes then：
Contrast subunit, the first audio categories character pair sound for will prestore in the frequency of the audio-frequency information and database
The frequency of frequency is compared, and calculates the similarity of the audio-frequency information and feature audio；
Determination subelement, for when the similarity reaches preset value, determining the audio categories of the audio-frequency information.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810096118.7A CN108389584B (en) | 2018-01-31 | 2018-01-31 | Sound analysis method and device |
| PCT/CN2018/091108 WO2019148737A1 (en) | 2018-01-31 | 2018-06-13 | Sound analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810096118.7A CN108389584B (en) | 2018-01-31 | 2018-01-31 | Sound analysis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108389584A true CN108389584A (en) | 2018-08-10 |
| CN108389584B CN108389584B (en) | 2021-03-19 |
Family
ID=63074916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810096118.7A Active CN108389584B (en) | 2018-01-31 | 2018-01-31 | Sound analysis method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108389584B (en) |
| WO (1) | WO2019148737A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108986056A (en) * | 2018-08-24 | 2018-12-11 | 潘小亮 | Content requirements judge system |
| CN109741609A (en) * | 2019-02-25 | 2019-05-10 | 南京理工大学 | A kind of motor vehicle whistle sound monitoring method based on microphone array |
| CN113496709A (en) * | 2020-04-07 | 2021-10-12 | 上海擎感智能科技有限公司 | In-vehicle sound effect remote online evaluation method and system, storage medium and server |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1033557A3 (en) * | 1999-03-04 | 2001-08-22 | Sony Corporation | Navigation apparatus |
| JP2003140546A (en) * | 2001-11-07 | 2003-05-16 | Chiri Geographic Information Service Co Ltd | Map recognition voice device for visually impaired person |
| CN102404667A (en) * | 2010-07-28 | 2012-04-04 | 株式会社泛泰 | Apparatus and method for merging acoustic object information |
| CN102435198A (en) * | 2010-09-28 | 2012-05-02 | 索尼公司 | Position information providing device, position information providing method, position information providing system, and program |
| CN103946733A (en) * | 2011-11-14 | 2014-07-23 | 谷歌公司 | Displaying sound indications on a wearable computing system |
| CN106251878A (en) * | 2016-08-26 | 2016-12-21 | 彭胜 | Meeting affairs voice recording device |
| CN106601260A (en) * | 2016-11-30 | 2017-04-26 | 中山大学 | Method for representing virtual sound of traffic noise map |
| WO2017155968A1 (en) * | 2016-03-07 | 2017-09-14 | 3M Innovative Properties Company | Intelligent safety monitoring and analytics system for personal protective equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1195972C (en) * | 2002-01-09 | 2005-04-06 | 英华达(上海)电子有限公司 | Method and devices for monitoring environment noise by using mobile phones |
| US20130094656A1 (en) * | 2011-10-16 | 2013-04-18 | Hei Tao Fung | Intelligent Audio Volume Control for Robot |
| CN107231476A (en) * | 2017-05-31 | 2017-10-03 | 深圳市邦华电子有限公司 | Mobile terminal and its scene mode setting method, device |
| CN107592129B (en) * | 2017-09-26 | 2019-10-18 | 广东小天才科技有限公司 | Early warning method and device for wearable equipment |
-
2018
- 2018-01-31 CN CN201810096118.7A patent/CN108389584B/en active Active
- 2018-06-13 WO PCT/CN2018/091108 patent/WO2019148737A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1033557A3 (en) * | 1999-03-04 | 2001-08-22 | Sony Corporation | Navigation apparatus |
| JP2003140546A (en) * | 2001-11-07 | 2003-05-16 | Chiri Geographic Information Service Co Ltd | Map recognition voice device for visually impaired person |
| CN102404667A (en) * | 2010-07-28 | 2012-04-04 | 株式会社泛泰 | Apparatus and method for merging acoustic object information |
| CN102435198A (en) * | 2010-09-28 | 2012-05-02 | 索尼公司 | Position information providing device, position information providing method, position information providing system, and program |
| CN103946733A (en) * | 2011-11-14 | 2014-07-23 | 谷歌公司 | Displaying sound indications on a wearable computing system |
| WO2017155968A1 (en) * | 2016-03-07 | 2017-09-14 | 3M Innovative Properties Company | Intelligent safety monitoring and analytics system for personal protective equipment |
| CN106251878A (en) * | 2016-08-26 | 2016-12-21 | 彭胜 | Meeting affairs voice recording device |
| CN106601260A (en) * | 2016-11-30 | 2017-04-26 | 中山大学 | Method for representing virtual sound of traffic noise map |
Non-Patent Citations (2)
| Title |
|---|
| ROBERT ALBRECHT: ""Auditory Distance Presentation in an Urban Augmented Reality Environment"", 《ACM TRANSACTIONS ON APPLIED PERCEPTION》 * |
| 哈哈呵呵好的: "《https://post.smzdm.com/p/632616/》", 1 December 2017 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108986056A (en) * | 2018-08-24 | 2018-12-11 | 潘小亮 | Content requirements judge system |
| CN109741609A (en) * | 2019-02-25 | 2019-05-10 | 南京理工大学 | A kind of motor vehicle whistle sound monitoring method based on microphone array |
| CN109741609B (en) * | 2019-02-25 | 2021-05-04 | 南京理工大学 | Motor vehicle whistling monitoring method based on microphone array |
| CN113496709A (en) * | 2020-04-07 | 2021-10-12 | 上海擎感智能科技有限公司 | In-vehicle sound effect remote online evaluation method and system, storage medium and server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108389584B (en) | 2021-03-19 |
| WO2019148737A1 (en) | 2019-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Nilsson | A-weighted sound pressure level as an indicator of short-term loudness or annoyance of road-traffic sound | |
| Klein et al. | Spectral and modulation indices for annoyance-relevant features of urban road single-vehicle pass-by noises | |
| CN108389584A (en) | Sound analysis method and device | |
| Lee et al. | Assessment of rural soundscapes with high-speed train noise | |
| Szychowska et al. | The influence of audio-visual interactions on the annoyance ratings for wind turbines | |
| US20170171681A1 (en) | Wireless exchange of data between devices in live events | |
| CN110488225A (en) | Indicating means, device, readable storage medium storing program for executing and the mobile terminal of sound bearing | |
| DE102013204798A1 (en) | AREA INFORMATION COMMUNICATION DEVICE | |
| Lemaitre et al. | A psychoacoustical study of wind buffeting noise | |
| CN107273086A (en) | Audio-frequency processing method and device based on navigation | |
| Oldoni et al. | The acoustic summary as a tool for representing urban sound environments | |
| Salleh et al. | Evaluation of annoyance and suitability of a back-up warning sound for electric vehicles | |
| Bolin et al. | The influence of background sounds on loudness and annoyance of wind turbine noise | |
| Kim et al. | Impact of adding artificially generated alert sound to hybrid electric vehicles on their detectability by pedestrians who are blind | |
| Preis et al. | Audio-visual interaction of environmental noise | |
| Davis et al. | Effects of secondary tasks on auditory detection and crossing thresholds in relation to approaching vehicle noises | |
| Doleschal et al. | Pleasantness and magnitude of tonal content of electric vehicle interior sounds containing subharmonics | |
| Harriet et al. | Auralisation of an urban soundscape | |
| CN104049869B (en) | A kind of data processing method and device | |
| Parizet et al. | NVH analysis techniques for design and optimization of hybrid and electric vehicles | |
| CN106601260B (en) | Virtual sound reproduction method of traffic noise map | |
| Sangberg | Adding noise to quiet electric and hybrid vehicels: An electric issue | |
| Torija et al. | Subjective dominance as a basis for selecting frequency weightings | |
| KR20210042851A (en) | audio recognition method, audio recognition apparatus, electronic equipment, computer readable storage medium and computer program | |
| Samardzic et al. | Sound source signal parameters in vehicles for determining speech transmission index |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |