CN108470564A - According to the artificial intelligence approach of audio identification personality characteristics - Google Patents
According to the artificial intelligence approach of audio identification personality characteristics Download PDFInfo
- Publication number
- CN108470564A CN108470564A CN201810290204.1A CN201810290204A CN108470564A CN 108470564 A CN108470564 A CN 108470564A CN 201810290204 A CN201810290204 A CN 201810290204A CN 108470564 A CN108470564 A CN 108470564A
- Authority
- CN
- China
- Prior art keywords
- audio
- personality
- analysis
- personality characteristics
- data
- 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.)
- Pending
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 15
- 238000013459 approach Methods 0.000 title claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims abstract description 69
- 238000000034 method Methods 0.000 claims abstract description 13
- 208000025967 Dissociative Identity disease Diseases 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 abstract description 13
- 238000005516 engineering process Methods 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 3
- 230000007115 recruitment Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003012 network analysis Methods 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
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- 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
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- 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
- G10L25/90—Pitch determination of speech signals
-
- 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
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/226—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics
- G10L2015/227—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics of the speaker; Human-factor methodology
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a kind of artificial intelligence approach according to audio identification personality characteristics, including personality characteristics range setting procedure, Audio feature analysis step, Analysis of personality characteristics steps;Personality characteristics range setting procedure presets the corresponding numberical range of multiple personality feature;For Audio feature analysis step to acquire basic data, basic data includes at least word speed analysis data, audio frequency feature analysis data, speech pause duration analysis data, high pitch proportion grading data and audio content analysis data;Collected basic data is calculated practical character trait score by software, practical character trait score is compared with the numberical range of preset multiple personality, obtains the personality characteristics of tester by Analysis of personality characteristics step.The present invention substantially increases efficiency and the accuracy of test and appraisal, it is only necessary to which audio file is input to in equipment or system with the invention software, you can obtains the result of personality characteristics test and appraisal.
Description
Technical field
The present invention relates to audio identification field, Analysis of personality characteristics fields more particularly to a kind of according to audio identification personality
The artificial intelligence approach of feature.
Background technology
In recent years, audio frequency identification technique is increasingly perfect, accuracy of identification higher, error smaller, but also audio frequency identification technique
It is applied to many fields, such as smart city, automatic navigator.
Personality characteristics test increasingly have been favored by people, many recruitment departments while receiving candidate's resume,
It is more desirable to that a Analysis of personality characteristics report can be received.Traditional Analysis of personality characteristics report source includes personality characteristics answer
Network analysis, artificial test and appraisal of video resume etc..Traditional personality characteristics answering system cannot meet existing demand, people
The authenticity of lattice feature answering system depends on the actual wishes of answer person, if answer person is not intended to employment department to know really
Oneself, then the result of answer can be greatly affected, to influence the judgement of Ren Zi departments.
The technology of the recording of video resume tends to be ripe, and many internet recruitment platforms support the recording of video resume, because
It is compared with word resume for video resume, can more really show the speciality of a people.Platform company is according in video resume
The language of personage is expressed, and analyzes personality characteristics, and provide people's property lattice test and evaluation report.Manual intervention is needed among these, is needed
The result of the data such as the word speed that personage speaks in artificial test video, test and appraisal can be by the shadow of test and appraisal personnel's experience and personality
It rings.
Invention content
To overcome disadvantages mentioned above, the purpose of the present invention is to provide a kind of efficiency and accuracy significantly providing test and appraisal
According to the artificial intelligence approach of audio identification personality characteristics.
In order to reach object above, the technical solution adopted by the present invention is:A kind of people according to audio identification personality characteristics
Work intelligent method, including personality characteristics range setting procedure, Audio feature analysis step, Analysis of personality characteristics step;The people
Lattice characteristic range setting procedure presets the corresponding numberical range of multiple personality feature;The Audio feature analysis step is used
To acquire basic data, the basic data includes at least word speed analysis data, audio frequency feature analysis data, speech pause
Duration analyzes data, high pitch proportion grading data and audio content analysis data;The Analysis of personality characteristics step, will acquire
To basic data practical character trait score is calculated by software, by the practical character trait score with preset
The numberical range of multiple personality be compared, obtain the personality characteristics of tester.
The present invention is according to the advantageous effect of the artificial intelligence approach of audio identification personality characteristics, and the present invention is by existing sound
Frequency identification technology and Personality evaluation technology are combined, and substantially increase efficiency and the accuracy of test and appraisal, it is only necessary to by audio file
It is input to in equipment or system with the invention software, you can obtain the result of personality characteristics test and appraisal.
Preferably, the word speed analysis data calculate the speed spoken in this section of voice by audio identification, obtain word speed
Characteristic value, unit are words per minute clocks.
Preferably, the audio frequency feature analysis data calculates audio frequency by audio volume control figure, obtains audio frequency
Rate characteristic value, unit are hertz.
Preferably, the analysis mode of the speech pause duration analysis data is that in audio volume control figure, analysis frequency is small
In the period of average waveform 2/3, and summation is calculated, obtains audio pause duration characteristics value, unit is the second.
Preferably, the high pitch proportion grading data take waveform to be more than the 2/3 of sound mean intensity in audio volume control figure
Period, and calculate summation, and calculate the accounting of high pitch period, obtain high pitch ratio characteristic value.
Preferably, the audio content analysis translates into word will go out voice content, and analyzes detection pass therein
Key word obtains audio content characteristic value.
Preferably, the practical character trait score is by the formula that software calculates:The practical character trait score
=word speed characteristic value × word speed personality index+audio frequency characteristic value × audio frequency personality index+audio pause duration characteristics
Value × audio pause duration personality index+high pitch ratio characteristic value × high pitch proportionality grid index+audio content characteristic value × sound
Frequently content type grid index.The sum of the score for calculating five kinds of features then obtains practical personality score, can accurately judge
The character trait of tester.
Preferably, the word speed personality index, audio frequency personality index, audio pause duration personality index, high pitch ratio
Example personality index and audio content personality index can be modified by program.The analysis index of character trait test and appraisal can
It adjusts, can be finely tuned at initial stage on probation, to achieve the purpose that more accurately to judge the character trait of a people.
Description of the drawings
Fig. 1 is the structural schematic diagram of the present embodiment.
Specific implementation mode
The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, so that advantages and features of the invention energy
It is easier to be readily appreciated by one skilled in the art, so as to make a clearer definition of the protection scope of the present invention.
Shown in attached drawing 1, the present embodiment is best embodiment:A kind of artificial intelligence according to audio identification personality characteristics
Energy method, including personality characteristics range setting procedure, Audio feature analysis step, Analysis of personality characteristics step;
Step 1, personality characteristics range setting procedure preset the corresponding numberical range of multiple personality feature, this implementation
Five kinds of personality characteristics are set in example, adaptability, sociability, opening, agreeableness, preciseness set adaptability accordingly
The corresponding numberical range of personality characteristics, the corresponding numberical range of sociability personality characteristics, the corresponding numerical value of open personality characteristics
Range, the corresponding numberical range of agreeableness personality characteristics, the corresponding numberical range of preciseness personality characteristics;
Step 2,2 step of Audio feature analysis, Audio feature analysis step is acquiring basic data, basic data packet
Include word speed analysis data, audio frequency feature analysis data, speech pause duration analysis data, high pitch proportion grading data and
Audio content analysis data.
Specifically include the following steps:
(a) audio-source is input in the system with the invention;
(b) basic information of audio, including audio volume control figure and the corresponding text of audio are identified using 1 technology of audio identification
Word information;
(c) text information is recorded on audio timeline, what is recorded in audio volume control figure is audio in different time
The intensity of point and the frequency of audio;
(d) audio volume control figure and word time shaft are analyzed, obtains five kinds of audio frequency characteristics in the invention, by analyzing audio
The result data of identification, the value for obtaining corresponding five kinds of audio frequency characteristics (analyze data, audio frequency feature analysis data, voice to stop
Immediately long analysis data, high pitch proportion grading data and audio content analysis data);It is worth further according to five kinds of audio frequency characteristics
Five kinds of person character trait's values.
Word speed analysis data calculate the speed spoken in this section of voice by audio identification, obtain word speed characteristic value, unit
It is words per minute clock;Audio frequency feature analysis data calculates audio frequency by audio volume control figure, obtains audio frequency characteristic value,
Unit is hertz;The analysis mode of speech pause duration analysis data is, in audio volume control figure, analysis frequency is less than average wave
The period of shape 2/3, and summation is calculated, audio pause duration characteristics value is obtained, unit is the second;High pitch proportion grading data, in sound
It takes waveform to be more than 2/3 period of sound mean intensity in frequency oscillogram, and calculates summation, and calculate the accounting of high pitch period,
Obtain high pitch ratio characteristic value;Audio content analysis translates into word will go out voice content, and analyzes detection pass therein
Key word obtains audio content characteristic value.
Collected basic data is passed through software meter by step 3,3 step of Analysis of personality characteristics, Analysis of personality characteristics step
Calculation obtains practical character trait score, and the numberical range of practical character trait score and preset multiple personality is compared
It is right, it by the analysis to five kinds of audio frequency characteristics, obtains the personality characteristics of tester, obtains relevant personality characteristics report.
Wherein, practical character trait score is by the formula that software calculates:Practical character trait score=word speed feature
Value × word speed personality index+audio frequency characteristic value × audio frequency personality index+audio pause duration characteristics value × audio is stopped
Immediately long personality index+high pitch ratio characteristic value × high pitch proportionality grid index+audio content characteristic value × audio content personality
Index.Word speed personality index, audio frequency personality index, audio pause duration personality index, high pitch proportionality grid index and
Audio content personality index can be modified by program.
That is, the computational methods of each character trait score are as follows:Adaptability score=word speed characteristic value × word speed personality refers to
Number+audio frequency characteristic value × audio frequency personality index+audio pause duration characteristics value × audio pause duration personality index+
High pitch ratio characteristic value × high pitch proportionality grid index+audio content characteristic value × audio content personality index, other four individual characteies
Lattice feature score formula is similar with this formula.
Wherein XnIndicate five kinds of signature analysis values, AnIndicate five kinds of adaptability
Signature analysis index.
Wherein XnIndicate five kinds of signature analysis values, BnIndicate five kinds of sociabilities
Signature analysis index.
Wherein XnIndicate five kinds of signature analysis values, CnIndicate five kinds of openings
Signature analysis index.
Wherein XnIndicate five kinds of signature analysis values, DnIndicate five kinds of agreeableness
Signature analysis index.
Wherein XnIndicate five kinds of signature analysis values, EnIndicate five kinds of preciseness
Signature analysis index.
The present invention can be combined existing audio frequency identification technique and Personality evaluation technology, substantially increase test and appraisal
Efficiency and accuracy.
The technical concepts and features of embodiment of above only to illustrate the invention, its object is to allow be familiar with technique
People understands present disclosure and is implemented, and it is not intended to limit the scope of the present invention, all according to spirit of that invention
The equivalent change or modification that essence is done should all cover within the scope of the present invention.
Claims (8)
1. a kind of artificial intelligence approach according to audio identification personality characteristics, it is characterised in that:It is set including personality characteristics range
Step, Audio feature analysis step, Analysis of personality characteristics step;
The personality characteristics range setting procedure presets the corresponding numberical range of multiple personality feature;
For the Audio feature analysis step to acquire basic data, the basic data includes at least word speed analysis data, sound
Frequent rate feature analysis data, speech pause duration analysis data, high pitch proportion grading data and audio content analysis data;
Practical character trait score is calculated by software in collected basic data by the Analysis of personality characteristics step,
The practical character trait score is compared with the numberical range of preset multiple personality, obtains the personality of tester
Feature.
2. the artificial intelligence approach according to claim 1 according to audio identification personality characteristics, it is characterised in that:Institute's predicate
Speed analysis data calculate the speed spoken in this section of voice by audio identification, obtain word speed characteristic value, unit is words per minute clock.
3. the artificial intelligence approach according to claim 1 according to audio identification personality characteristics, it is characterised in that:The sound
Frequent rate feature analysis data calculates audio frequency by audio volume control figure, obtains audio frequency characteristic value, unit is hertz.
4. the artificial intelligence approach according to claim 1 according to audio identification personality characteristics, it is characterised in that:Institute's predicate
The analysis mode of sound pause duration analysis data is, in audio volume control figure, analysis frequency is less than the period of average waveform 2/3,
And summation is calculated, audio pause duration characteristics value is obtained, unit is the second.
5. the artificial intelligence approach according to claim 1 according to audio identification personality characteristics, it is characterised in that:The height
Sound proportion grading data take waveform to be more than 2/3 period of sound mean intensity in audio volume control figure, and calculate summation, and
The accounting for calculating the high pitch period, obtains high pitch ratio characteristic value.
6. the artificial intelligence approach according to claim 1 according to audio identification personality characteristics, it is characterised in that:The sound
Frequency content analysis translates into word will go out voice content, and analyzes detection keyword therein, obtains audio content feature
Value.
7. the artificial intelligence approach according to claim 1 according to audio identification personality characteristics, it is characterised in that:The reality
Border character trait score is by the formula that software calculates:The practical character trait score=word speed characteristic value × word speed personality
Index+audio frequency characteristic value × audio frequency personality index+audio pause duration characteristics value × audio pause duration personality refers to
Number+high pitch ratio characteristic value × high pitch proportionality grid index+audio content characteristic value × audio content personality index.
8. the artificial intelligence approach according to claim 7 according to audio identification personality characteristics, it is characterised in that:Institute's predicate
Fast personality index, audio frequency personality index, audio pause duration personality index, high pitch proportionality grid index and audio content
Personality index can be modified by program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810290204.1A CN108470564A (en) | 2018-04-03 | 2018-04-03 | According to the artificial intelligence approach of audio identification personality characteristics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810290204.1A CN108470564A (en) | 2018-04-03 | 2018-04-03 | According to the artificial intelligence approach of audio identification personality characteristics |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108470564A true CN108470564A (en) | 2018-08-31 |
Family
ID=63262697
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810290204.1A Pending CN108470564A (en) | 2018-04-03 | 2018-04-03 | According to the artificial intelligence approach of audio identification personality characteristics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108470564A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110111810A (en) * | 2019-04-29 | 2019-08-09 | 华院数据技术(上海)有限公司 | Voice personality prediction technique based on convolutional neural networks |
CN116631446A (en) * | 2023-07-26 | 2023-08-22 | 上海迎智正能文化发展有限公司 | Behavior mode analysis method and system based on speech analysis |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5422656A (en) * | 1993-11-01 | 1995-06-06 | International Business Machines Corp. | Personal communicator having improved contrast control for a liquid crystal, touch sensitive display |
JP2000286936A (en) * | 1999-03-31 | 2000-10-13 | Nec Saitama Ltd | Mobile terminal device |
WO2001013360A1 (en) * | 1999-08-17 | 2001-02-22 | Glenayre Electronics, Inc. | Pitch and voicing estimation for low bit rate speech coders |
CN103634472A (en) * | 2013-12-06 | 2014-03-12 | 惠州Tcl移动通信有限公司 | Method, system and mobile phone for judging mood and character of user according to call voice |
CN107293310A (en) * | 2017-06-28 | 2017-10-24 | 上海航动科技有限公司 | A kind of user emotion analysis method and system |
-
2018
- 2018-04-03 CN CN201810290204.1A patent/CN108470564A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5422656A (en) * | 1993-11-01 | 1995-06-06 | International Business Machines Corp. | Personal communicator having improved contrast control for a liquid crystal, touch sensitive display |
JP2000286936A (en) * | 1999-03-31 | 2000-10-13 | Nec Saitama Ltd | Mobile terminal device |
WO2001013360A1 (en) * | 1999-08-17 | 2001-02-22 | Glenayre Electronics, Inc. | Pitch and voicing estimation for low bit rate speech coders |
CN103634472A (en) * | 2013-12-06 | 2014-03-12 | 惠州Tcl移动通信有限公司 | Method, system and mobile phone for judging mood and character of user according to call voice |
CN107293310A (en) * | 2017-06-28 | 2017-10-24 | 上海航动科技有限公司 | A kind of user emotion analysis method and system |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110111810A (en) * | 2019-04-29 | 2019-08-09 | 华院数据技术(上海)有限公司 | Voice personality prediction technique based on convolutional neural networks |
CN110111810B (en) * | 2019-04-29 | 2020-12-18 | 华院数据技术(上海)有限公司 | Voice personality prediction method based on convolutional neural network |
CN116631446A (en) * | 2023-07-26 | 2023-08-22 | 上海迎智正能文化发展有限公司 | Behavior mode analysis method and system based on speech analysis |
CN116631446B (en) * | 2023-07-26 | 2023-11-03 | 上海迎智正能文化发展有限公司 | Behavior mode analysis method and system based on speech analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105184315B (en) | A kind of quality inspection processing method and system | |
US11276407B2 (en) | Metadata-based diarization of teleconferences | |
US9058816B2 (en) | Emotional and/or psychiatric state detection | |
CN106611604B (en) | Automatic voice superposition detection method based on deep neural network | |
CN103559892B (en) | Oral evaluation method and system | |
CN103559894B (en) | Oral evaluation method and system | |
CN110457432A (en) | Interview methods of marking, device, equipment and storage medium | |
CN110308485B (en) | Microseismic signal classification method and device based on deep learning and storage medium | |
CN109147765A (en) | Audio quality comprehensive evaluating method and system | |
CN111739559A (en) | Speech early warning method, device, equipment and storage medium | |
CN107919137A (en) | The long-range measures and procedures for the examination and approval, device, equipment and readable storage medium storing program for executing | |
Brandes | Feature vector selection and use with hidden Markov models to identify frequency-modulated bioacoustic signals amidst noise | |
CN102623009A (en) | Abnormal emotion automatic detection and extraction method and system on basis of short-time analysis | |
CN103440864A (en) | Personality characteristic forecasting method based on voices | |
CN108305619A (en) | Voice data collection training method and apparatus | |
Callan et al. | Self-organizing map for the classification of normal and disordered female voices | |
Morrison et al. | Introduction to forensic voice comparison | |
CN113807103B (en) | Recruitment method, device, equipment and storage medium based on artificial intelligence | |
CN109545027B (en) | Training platform, crew simulation training method and device | |
Cordero et al. | Automated speech recognition in controller communications applied to workload measurement | |
CN103054586A (en) | Chinese speech automatic audiometric method based on Chinese speech audiometric dynamic word list | |
CN110782902A (en) | Audio data determination method, apparatus, device and medium | |
CN108470564A (en) | According to the artificial intelligence approach of audio identification personality characteristics | |
CN113823293A (en) | Speaker recognition method and system based on voice enhancement | |
US20220157322A1 (en) | Metadata-based diarization of teleconferences |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180831 |