CN108269590A - Vocal cord recovery scoring method and device - Google Patents
Vocal cord recovery scoring method and device Download PDFInfo
- Publication number
- CN108269590A CN108269590A CN201810045029.XA CN201810045029A CN108269590A CN 108269590 A CN108269590 A CN 108269590A CN 201810045029 A CN201810045029 A CN 201810045029A CN 108269590 A CN108269590 A CN 108269590A
- Authority
- CN
- China
- Prior art keywords
- similarity
- under
- characteristic parameter
- feature vector
- processing
- 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
- 238000011084 recovery Methods 0.000 title claims abstract description 52
- 210000001260 vocal cord Anatomy 0.000 title claims abstract description 45
- 238000013077 scoring method Methods 0.000 title abstract 2
- 238000012545 processing Methods 0.000 claims abstract description 59
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000012360 testing method Methods 0.000 claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 15
- 230000036541 health Effects 0.000 claims abstract description 5
- 238000010606 normalization Methods 0.000 claims abstract description 4
- 230000001755 vocal effect Effects 0.000 claims description 51
- 230000003862 health status Effects 0.000 claims description 31
- 230000008569 process Effects 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 14
- 238000005070 sampling Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 238000001356 surgical procedure Methods 0.000 description 2
- 208000037062 Polyps Diseases 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method 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
- 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
- G10L25/66—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 for extracting parameters related to health condition
-
- 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
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Instructional Devices (AREA)
Abstract
The invention provides a vocal cord recovery scoring method and a vocal cord recovery scoring device, which solve the technical problems that patients are painful due to the existing recovery examination through an electronic laryngoscope, and the recovery condition of vocal cords is difficult to describe by the subjectivity of the patients, wherein the method comprises the following steps: acquiring a test audio of a patient in a recovery state; extracting a first voice characteristic parameter in the test audio; training by using the first voice characteristic parameter to establish a first UBM model and obtain a voiceprint characteristic vector in a recovery state; acquiring a voiceprint feature vector in a health state in a database; obtaining the similarity of the voiceprint feature vector in the recovery state and the voiceprint feature vector in the health state in the database through probability linear discriminant analysis; carrying out normalization processing on the similarity to determine the interval range of the similarity; and obtaining the score of the patient in the recovery state according to the interval range of the similarity.
Description
Technical field
The present invention relates to sound groove recognition technology in e fields more particularly to a kind of vocal cords to restore methods of marking and device.
Background technology
In certain professional field of acoustics, such as professional singer, announcer, teacher of the dubbing etc., the stability requirement to sound
It is very high, for a long time excessively vocal cord injury is inevitably caused with sound.Usually slight vocal cords are damaged and can restore.Compare tight
Weight vocal cord injury, if caused by being clearly vocal nodule or polyp, in the case where medication effect is bad, need into
Row surgical removal.
At present for the recovery situation after operation on vocal cord, objective evaluation of often having no idea is typically only capable to according to doctor's
(such as electrolaryngoscope) is checked to give out specific recovery situation, lacks objective quantizating index doctor to be assisted to judge.
Restore to check to solve existing do by electrolaryngoscope therefore it provides a kind of vocal cords restore methods of marking and device
Patient can be made very painful, and patient's subjectivity also be difficult to description vocal cords recovery situation the technical issues of.
Invention content
The present invention provides a kind of vocal cords to restore methods of marking and device, solves existing done by electrolaryngoscope and restores
The technical issues of inspection can make patient very painful, and patient's subjectivity also is difficult to the recovery situation of description vocal cords.
The present invention provides a kind of vocal cords to restore methods of marking, including：
Obtain testing audio of the patient under recovery state；
Extract the first speech characteristic parameter in the testing audio；
Using the first speech characteristic parameter training to establish the first UBM model, and the vocal print under the state that is restored
Characteristic vector；
Obtain the vocal print feature vector under the health status in database；
The health status being restored by probability linear discriminant analysis in the vocal print feature vector sum database under state
Under vocal print feature vector similarity；
The similarity is normalized, determines the interval range of the similarity；
Score of the patient under recovery state is obtained according to the interval range of the similarity.
Preferably, it is further included before the testing audio for obtaining patient under recovery state：
Obtain sample audio of the patient under health status；
Sampling processing and/or preemphasis processing and/or pre-filtering processing and/or windowing process are carried out to the sample audio
And/or end-point detection processing.
Extract the second speech characteristic parameter in the sample audio；
Using the second speech characteristic parameter training to establish the second UBM model, and obtain the vocal print under health status
Characteristic vector is simultaneously stored into database.
Preferably, after the testing audio for obtaining patient under recovery state, the extraction testing audio
In the first speech characteristic parameter before further include：
Sampling processing and/or preemphasis processing and/or pre-filtering processing and/or windowing process are carried out to the testing audio
And/or end-point detection processing.
Preferably, first speech characteristic parameter and second speech characteristic parameter are mel-frequency cepstrum system
Number.
The present invention provides a kind of vocal cords to restore scoring apparatus, including：
First acquisition unit, for obtaining testing audio of the patient under recovery state；
First extraction unit, for extracting the first speech characteristic parameter in the testing audio；
First modeling unit, for, to establish the first UBM model, and being obtained using the first speech characteristic parameter training
Vocal print feature vector under recovery state；
Second acquisition unit, for obtaining the vocal print feature vector under the health status in database；
Similarity unit, for passing through the vocal print feature vector sum data that probability linear discriminant analysis is restored under state
The similarity of vocal print feature vector under health status in library；
Normalization unit for the similarity to be normalized, determines the interval range of the similarity；
Score unit, for obtaining score of the patient under recovery state according to the interval range of the similarity.
It is further included preferably, a kind of vocal cords provided by the invention restore scoring apparatus：
Third acquiring unit, for obtaining sample audio of the patient under health status；
First processing units, for carrying out sampling processing and/or preemphasis processing and/or pre-filtering to the sample audio
Processing and/or windowing process and/or end-point detection processing.
Second extraction unit, for extracting the second speech characteristic parameter in the sample audio；
Second modeling unit, for, to establish the second UBM model, and being obtained using the second speech characteristic parameter training
Vocal print feature vector under health status is simultaneously stored into database.
It is further included preferably, a kind of vocal cords provided by the invention restore scoring apparatus：
Second processing unit, for carrying out sampling processing and/or preemphasis processing and/or pre-filtering to the testing audio
Processing and/or windowing process and/or end-point detection processing.
Preferably, first speech characteristic parameter and second speech characteristic parameter are mel-frequency cepstrum system
Number.
As can be seen from the above technical solutions, the present invention has the following advantages：
The present invention provides a kind of vocal cords to restore methods of marking, including：Obtain testing audio of the patient under recovery state；
Extract the first speech characteristic parameter in the testing audio；Using the first speech characteristic parameter training to establish first
UBM model, and the vocal print feature vector under the state that is restored；Obtain the vocal print feature arrow under the health status in database
Amount；The sound being restored under the health status in the vocal print feature vector sum database under state by probability linear discriminant analysis
The similarity of line characteristic vector；The similarity is normalized, determines the interval range of the similarity；According to institute
The interval range for stating similarity obtains score of the patient under recovery state.
In the present invention, patient is obtained by UBM model (Universal Background Model, universal background model)
Vocal print feature vector under recovery state, will be under the health status in the vocal print feature vector under recovery state and database
Vocal print feature vector is compared, and similarity between the two is obtained by probability linear discriminant analysis, finally to similarity into
Row normalized obtains the interval range of similarity, and the recovery shape to patient can be obtained according to the interval range of similarity
The scoring of state realizes and directly judges the recovery situations of patient's vocal cords according to scoring, solves and existing is done by electrolaryngoscope
The technical issues of restoring to check can make patient very painful, and patient's subjectivity also is difficult to the recovery situation of description vocal cords.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention, for those of ordinary skill in the art, without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is the flow diagram of one embodiment that a kind of vocal cords provided by the invention restore methods of marking；
Fig. 2 is the flow diagram for another embodiment that a kind of vocal cords provided by the invention restore methods of marking；
Fig. 3 is the structure diagram of one embodiment that a kind of vocal cords provided by the invention restore scoring apparatus.
Specific embodiment
An embodiment of the present invention provides a kind of vocal cords to restore methods of marking and device, solves and existing passes through electrolaryngoscope
The technical issues of doing recovery and checking can make patient very painful, and patient's subjectivity also is difficult to the recovery situation of description vocal cords.
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without making creative work
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, an embodiment of the present invention provides one embodiment that a kind of vocal cords restore methods of marking, including：
101st, testing audio of the patient under recovery state is obtained；
102nd, the first speech characteristic parameter in testing audio is extracted；
103rd, using the first speech characteristic parameter training to establish the first UBM model, and the vocal print under the state that is restored
Characteristic vector；
104th, the vocal print feature vector under the health status in database is obtained；
105th, the health being restored by probability linear discriminant analysis in the vocal print feature vector sum database under state
The similarity of vocal print feature vector under state；
106th, similarity is normalized, determines the interval range of similarity；
107th, score of the patient under recovery state is obtained according to the interval range of similarity.
In the embodiment of the present invention, obtained by UBM model (Universal Background Model, universal background model)
To vocal print feature vector of the patient under recovery state, by the healthy shape in the vocal print feature vector under recovery state and database
Vocal print feature vector under state is compared, and similarity between the two is obtained by probability linear discriminant analysis, finally to phase
It is normalized like degree, obtains the interval range of similarity, can obtained according to the interval range of similarity to patient's
The scoring of recovery state realizes and directly judges the recovery situations of patient's vocal cords according to scoring, solves and existing passes through electronics
The technical issues of laryngoscope, which does recovery and checks, can make patient very painful, and patient's subjectivity also is difficult to the recovery situation of description vocal cords.
It is that one embodiment that a kind of vocal cords provided by the invention restore methods of marking illustrates above, will be described below
Another embodiment that a kind of vocal cords provided by the invention restore methods of marking illustrates.
Referring to Fig. 2, an embodiment of the present invention provides another embodiment that a kind of vocal cords restore methods of marking, including：
201st, sample audio of the patient under health status is obtained；
It should be noted that before patient carries out operation on vocal cord, sample audio of the patient under health status is obtained.
202nd, sampling processing and/or preemphasis processing and/or pre-filtering processing and/or windowing process are carried out to sample audio
And/or end-point detection processing；
It should be noted that obtaining patient after the sample audio under health status, sample audio is sampled
Processing and/or preemphasis processing and/or pre-filtering processing and/or windowing process and/or end-point detection processing.
203rd, the second speech characteristic parameter in sample audio is extracted；
It should be noted that after handling sample audio, the second speech characteristic parameter in sample audio is extracted,
In the present embodiment, the second speech characteristic parameter is mel-frequency cepstrum coefficient.
204th, using the second speech characteristic parameter training to establish the second UBM model, and the vocal print under health status is obtained
Characteristic vector is simultaneously stored into database；
It should be noted that using the second speech characteristic parameter, i.e., mel-frequency cepstrum coefficient is trained and establishes the 2nd UBM
Model (Universal Background Model, universal background model), obtains according to the second UBM model under health status
Vocal print feature vector is simultaneously stored into database, for subsequently comparing.
205th, testing audio of the patient under recovery state is obtained；
It should be noted that obtain patient after surgery, the testing audio under recovery state.
206th, sampling processing and/or preemphasis processing and/or pre-filtering processing and/or windowing process are carried out to testing audio
And/or end-point detection processing；
It should be noted that after testing audio of the patient under recovery state is obtained, testing audio is sampled
Processing and/or preemphasis processing and/or pre-filtering processing and/or windowing process and/or end-point detection processing.
207th, the first speech characteristic parameter in testing audio is extracted；
Ten illustrated are needed, after handling testing audio, extract the first speech characteristic parameter in testing audio,
In the present embodiment, the first speech characteristic parameter is mel-frequency cepstrum coefficient.
208th, using the first speech characteristic parameter training to establish the first UBM model, and the vocal print under the state that is restored
Characteristic vector；
It should be noted that using the first speech characteristic parameter, i.e., mel-frequency cepstrum coefficient is trained and establishes the first UBM
Model (Universal Background Model, universal background model), is restored according to the first UBM model under state
Vocal print feature vector.
209th, the vocal print feature vector under the health status in database is obtained；
It should be noted that get vocal print feature vector of the patient under health status in database.
210th, the health being restored by probability linear discriminant analysis in the vocal print feature vector sum database under state
The similarity of vocal print feature vector under state；
It should be noted that the vocal print feature vector sum database being restored by probability linear discriminant analysis under state
In health status under vocal print feature vector similarity, probability linear discriminant analysis (PLDA, Probabilistic
Linear Discriminant Analysis) it is a kind of channel compensation algorithm based on vocal print feature vector, two can be obtained
Similarity between a vocal print feature vector.
211st, similarity is normalized, determines the interval range of similarity；
It should be noted that by being normalized by the similarity that probability linear discriminant analysis obtains, phase is determined
Like the interval range of degree, to ensure similitude, in the present embodiment, the interval range of [0%~100%] as similarity is taken.
212nd, score of the patient under recovery state is obtained according to the interval range of similarity；
It should be noted that according to the interval range of similarity, patient's current score of vocal cords under recovery state is determined,
Score is higher, and the recovery state for representing patient is better.
It is that another embodiment for restoring methods of marking to a kind of vocal cords provided by the invention illustrates above, below will
The one embodiment for restoring scoring apparatus to a kind of vocal cords provided by the invention illustrates.
Referring to Fig. 3, the present invention provides one embodiment that a kind of vocal cords restore scoring apparatus, including：
Third acquiring unit 301, for obtaining sample audio of the patient under health status；
First processing units 302, for carrying out sampling processing and/or preemphasis processing and/or pre-filtering to sample audio
Processing and/or windowing process and/or end-point detection processing；
Second extraction unit 303, for extracting the second speech characteristic parameter in sample audio；
Second modeling unit 304, for, to establish the second UBM model, and being obtained using the second speech characteristic parameter training
Vocal print feature vector under health status is simultaneously stored into database.
First acquisition unit 305, for obtaining testing audio of the patient under recovery state；
Second processing unit 306, for carrying out sampling processing and/or preemphasis processing and/or pre-filtering to testing audio
Processing and/or windowing process and/or end-point detection processing；
First extraction unit 307, for extracting the first speech characteristic parameter in testing audio；
First modeling unit 308, for, to establish the first UBM model, and being obtained using the first speech characteristic parameter training
Vocal print feature vector under recovery state；
Second acquisition unit 309, for obtaining the vocal print feature vector under the health status in database；
Similarity unit 310, for passing through the vocal print feature vector sum that probability linear discriminant analysis is restored under state
The similarity of vocal print feature vector under health status in database；
Normalization unit 311 for similarity to be normalized, determines the interval range of similarity；
Score unit 312, for obtaining score of the patient under recovery state according to the interval range of similarity.
It is apparent to those skilled in the art that for convenience and simplicity of description, the device of foregoing description
With the specific work process of unit, the corresponding process in preceding method embodiment can be referred to, details are not described herein.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
The present invention is described in detail, it will be understood by those of ordinary skill in the art that：It still can be to aforementioned each implementation
Technical solution recorded in example modifies or carries out equivalent replacement to which part technical characteristic；And these modification or
It replaces, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution.
Claims (8)
1. a kind of vocal cords restore methods of marking, which is characterized in that including：
Obtain testing audio of the patient under recovery state；
Extract the first speech characteristic parameter in the testing audio；
Using the first speech characteristic parameter training to establish the first UBM model, and the vocal print feature under the state that is restored
Vector；
Obtain the vocal print feature vector under the health status in database；
It is restored under the health status in the vocal print feature vector sum database under state by probability linear discriminant analysis
The similarity of vocal print feature vector；
The similarity is normalized, determines the interval range of the similarity；
Score of the patient under recovery state is obtained according to the interval range of the similarity.
2. vocal cords according to claim 1 restore methods of marking, which is characterized in that the acquisition patient is under recovery state
Testing audio before further include：
Obtain sample audio of the patient under health status；
The sample audio is carried out sampling processing and/or preemphasis processing and/or pre-filtering processing and/or windowing process and/
Or end-point detection processing.
Extract the second speech characteristic parameter in the sample audio；
Using the second speech characteristic parameter training to establish the second UBM model, and obtain the vocal print feature under health status
Vector is simultaneously stored into database.
3. vocal cords according to claim 1 restore methods of marking, which is characterized in that the acquisition patient is under recovery state
Testing audio after, further included before the first speech characteristic parameter in the extraction testing audio：
The testing audio is carried out sampling processing and/or preemphasis processing and/or pre-filtering processing and/or windowing process and/
Or end-point detection processing.
4. vocal cords as claimed in any of claims 1 to 3 restore methods of marking, which is characterized in that first language
Sound characteristic parameter and second speech characteristic parameter are mel-frequency cepstrum coefficient.
5. a kind of vocal cords restore scoring apparatus, which is characterized in that including：
First acquisition unit, for obtaining testing audio of the patient under recovery state；
First extraction unit, for extracting the first speech characteristic parameter in the testing audio；
First modeling unit, for, to establish the first UBM model, and being restored using the first speech characteristic parameter training
Vocal print feature vector under state；
Second acquisition unit, for obtaining the vocal print feature vector under the health status in database；
Similarity unit, for passing through in the vocal print feature vector sum database that probability linear discriminant analysis is restored under state
Health status under vocal print feature vector similarity；
Normalization unit for the similarity to be normalized, determines the interval range of the similarity；
Score unit, for obtaining score of the patient under recovery state according to the interval range of the similarity.
6. vocal cords according to claim 5 restore scoring apparatus, which is characterized in that further include：
Third acquiring unit, for obtaining sample audio of the patient under health status；
First processing units are handled for carrying out sampling processing and/or preemphasis processing and/or pre-filtering to the sample audio
And/or windowing process and/or end-point detection are handled.
Second extraction unit, for extracting the second speech characteristic parameter in the sample audio；
Second modeling unit, for, to establish the second UBM model, and obtaining health using the second speech characteristic parameter training
Vocal print feature vector under state is simultaneously stored into database.
7. vocal cords according to claim 5 restore scoring apparatus, which is characterized in that further include：
Second processing unit is handled for carrying out sampling processing and/or preemphasis processing and/or pre-filtering to the testing audio
And/or windowing process and/or end-point detection are handled.
8. the vocal cords according to any one in claim 5 to 7 restore scoring apparatus, which is characterized in that first language
Sound characteristic parameter and second speech characteristic parameter are mel-frequency cepstrum coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810045029.XA CN108269590A (en) | 2018-01-17 | 2018-01-17 | Vocal cord recovery scoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810045029.XA CN108269590A (en) | 2018-01-17 | 2018-01-17 | Vocal cord recovery scoring method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108269590A true CN108269590A (en) | 2018-07-10 |
Family
ID=62775782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810045029.XA Pending CN108269590A (en) | 2018-01-17 | 2018-01-17 | Vocal cord recovery scoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108269590A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102849A (en) * | 2019-06-18 | 2020-12-18 | 成都医学院 | Sound analysis method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060116878A1 (en) * | 2004-11-30 | 2006-06-01 | Kenji Nagamine | Asthma diagnostic apparatus, asthma diagnostic method, and storage medium storing asthma diagnostic program |
| CN103093759A (en) * | 2013-01-16 | 2013-05-08 | 东北大学 | Device and method of voice detection and evaluation based on mobile terminal |
| CN103258545A (en) * | 2012-12-20 | 2013-08-21 | 苏州大学 | Pathological voice subdivision method |
| CN106098068A (en) * | 2016-06-12 | 2016-11-09 | 腾讯科技（深圳）有限公司 | A kind of method for recognizing sound-groove and device |
| CN106941005A (en) * | 2017-02-24 | 2017-07-11 | 华南理工大学 | A kind of vocal cords method for detecting abnormality based on speech acoustics feature |
| EP3200188A1 (en) * | 2016-01-27 | 2017-08-02 | Telefonica Digital España, S.L.U. | Computer implemented methods for assessing a disease through voice analysis and computer programs thereof |
| CN107274906A (en) * | 2017-06-28 | 2017-10-20 | 百度在线网络技术（北京）有限公司 | Voice information processing method, device, terminal and storage medium |
| CN206726760U (en) * | 2017-05-05 | 2017-12-08 | 京东方科技集团股份有限公司 | Microphone, data processor and monitoring system |
-
2018
- 2018-01-17 CN CN201810045029.XA patent/CN108269590A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060116878A1 (en) * | 2004-11-30 | 2006-06-01 | Kenji Nagamine | Asthma diagnostic apparatus, asthma diagnostic method, and storage medium storing asthma diagnostic program |
| CN103258545A (en) * | 2012-12-20 | 2013-08-21 | 苏州大学 | Pathological voice subdivision method |
| CN103093759A (en) * | 2013-01-16 | 2013-05-08 | 东北大学 | Device and method of voice detection and evaluation based on mobile terminal |
| EP3200188A1 (en) * | 2016-01-27 | 2017-08-02 | Telefonica Digital España, S.L.U. | Computer implemented methods for assessing a disease through voice analysis and computer programs thereof |
| CN106098068A (en) * | 2016-06-12 | 2016-11-09 | 腾讯科技（深圳）有限公司 | A kind of method for recognizing sound-groove and device |
| CN106941005A (en) * | 2017-02-24 | 2017-07-11 | 华南理工大学 | A kind of vocal cords method for detecting abnormality based on speech acoustics feature |
| CN206726760U (en) * | 2017-05-05 | 2017-12-08 | 京东方科技集团股份有限公司 | Microphone, data processor and monitoring system |
| CN107274906A (en) * | 2017-06-28 | 2017-10-20 | 百度在线网络技术（北京）有限公司 | Voice information processing method, device, terminal and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| DANIEL CARCIA-ROMERO 等: ""Analysis of I-vector Lenght Normalization in Speaker Recognition Systems"", 《CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011》 * |
| 王尔玉: ""基于若干声纹信息空间的说话人识别技术研究"", 《中国博士学位论文全文数据库(信息科技辑)》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102849A (en) * | 2019-06-18 | 2020-12-18 | 成都医学院 | Sound analysis method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hassan et al. | COVID-19 detection system using recurrent neural networks | |
| Sharma et al. | Coswara--a database of breathing, cough, and voice sounds for COVID-19 diagnosis | |
| CN106725532A (en) | Depression automatic evaluation system and method based on phonetic feature and machine learning | |
| CN109330584B (en) | Electrocardiosignal identity recognition method and system based on dictionary learning and sparse representation | |
| CN113537005B (en) | Online examination student behavior analysis method based on attitude estimation | |
| US20210298711A1 (en) | Audio biomarker for virtual lung function assessment and auscultation | |
| CN106782603A (en) | Intelligent sound evaluating method and system | |
| Chandler et al. | Overcoming the bottleneck in traditional assessments of verbal memory: Modeling human ratings and classifying clinical group membership | |
| CN112017744A (en) | Electronic case automatic generation method, device, equipment and storage medium | |
| Marini et al. | IDEA: an Italian dysarthric speech database | |
| CN108269590A (en) | Vocal cord recovery scoring method and device | |
| CN109036506A (en) | Monitoring and managing method, electronic device and the readable storage medium storing program for executing of internet medical treatment interrogation | |
| US20230172526A1 (en) | Automated assessment of cognitive and speech motor impairment | |
| CN109378082A (en) | Monitoring and managing method, electronic device and the readable storage medium storing program for executing of internet medical treatment interrogation | |
| CN108550394A (en) | Disease diagnosis method and device based on voiceprint recognition | |
| CN115831352B (en) | Detection method based on dynamic texture features and time slicing weight network | |
| CN111415680A (en) | Method for generating anxiety prediction model based on voice and anxiety prediction system | |
| CN114238558A (en) | Quality inspection method and device for electronic medical record, storage medium and equipment | |
| Zuo et al. | A Cross Gender and Cross Lingual Study on Acoustic Features for Stress Recognition in Speech. | |
| CN115273176A (en) | Pain multi-algorithm objective assessment method based on vital signs and expressions | |
| CN108831560A (en) | A kind of method and apparatus of determining medical data attribute data | |
| CN113936663A (en) | Method for detecting difficult airway, electronic device and storage medium thereof | |
| CN114420303A (en) | Novel new crown auxiliary screening method based on sound characteristics | |
| EP4078621A1 (en) | Diagnosing respiratory maladies from subject sounds | |
| Thotappa et al. | Reference and automatic marking of glottal opening instants using egg signal |
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: 20180710 |