CN109064789A - A kind of adjoint cerebral palsy speaks with a lisp supplementary controlled system and method, assistor - Google Patents
A kind of adjoint cerebral palsy speaks with a lisp supplementary controlled system and method, assistor Download PDFInfo
- Publication number
- CN109064789A CN109064789A CN201810939343.2A CN201810939343A CN109064789A CN 109064789 A CN109064789 A CN 109064789A CN 201810939343 A CN201810939343 A CN 201810939343A CN 109064789 A CN109064789 A CN 109064789A
- Authority
- CN
- China
- Prior art keywords
- lisp
- client
- cerebral palsy
- pronunciation
- adjoint
- 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
- 206010008129 cerebral palsy Diseases 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000010801 machine learning Methods 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 4
- 230000005540 biological transmission Effects 0.000 claims description 7
- 230000008439 repair process Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 abstract description 19
- 230000000694 effects Effects 0.000 abstract description 16
- 238000004891 communication Methods 0.000 abstract description 6
- 208000027765 speech disease Diseases 0.000 description 23
- 230000008569 process Effects 0.000 description 5
- 206010033799 Paralysis Diseases 0.000 description 4
- 239000008186 active pharmaceutical agent Substances 0.000 description 4
- 210000004556 brain Anatomy 0.000 description 4
- 239000003814 drug Substances 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 201000008482 osteoarthritis Diseases 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 206010061623 Adverse drug reaction Diseases 0.000 description 1
- 208000030453 Drug-Related Side Effects and Adverse reaction Diseases 0.000 description 1
- 206010021118 Hypotonia Diseases 0.000 description 1
- 208000030137 articulation disease Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 206010009259 cleft lip Diseases 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 208000017561 flaccidity Diseases 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003254 palate Anatomy 0.000 description 1
- 238000010008 shearing Methods 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
- 208000011293 voice disease Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/04—Electrically-operated educational appliances with audible presentation of the material to be studied
-
- 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
- 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
- G10L21/003—Changing voice quality, e.g. pitch or formants
- G10L21/007—Changing voice quality, e.g. pitch or formants characterised by the process used
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention belongs to communication control and communications processing field, discloses a kind of adjoint cerebral palsy and speak with a lisp supplementary controlled system and method, assistor.Client: for acquiring the audio data file for speaking with a lisp crowd's pronunciation.Server end: connecting with client, for the corresponding text file of client to be carried out machine learning, forms the model of a fuzzy pronunciation of replacement repairing, model is issued to client.Product significant effect of the invention and cheap, can effectively help those that cannot bear the people of operation or the high expense of speech rehabilitation training;The crowd for making pronunciation fuzzy has other selections other than performing the operation and speech rehabilitation is trained;It is compared with operation, speech rehabilitation training, the voice restoration of this product has accomplished instantaneity, has saved patient's a large amount of time, can be used as a auxiliary tool of operation or speech rehabilitation training.
Description
Technical field
The invention belongs to communication control and communications processing field more particularly to a kind of adjoint cerebral palsy speak with a lisp it is auxiliary
Help control system and method, assistor.
Background technique
Currently, the prior art commonly used in the trade is such thatCommunication exchange is part indispensable in life, but simultaneously
Be not everyone can have no obstacle with other people communication exchanges, this kind of crowd's pronunciation is fuzzy, such as functional articulation disorder, palate
Split-voice disorder, listen barrier-disfluency, language retardation, brain paralysis disfluency etc., most of their generation from
The diseases such as self-closing disease, brain paralysis, harelip.Wherein patients with cerebral palsy normally behaves as: speaking with a lisp, feeblemindedness, slow in reacting, nozzle
Inability is chewed, is salivated, limbs fatigue, continuous inability of flaccidity of extremities etc..Currently, there is no such a directly help brain paralysis to suffer from the market
Person solves the problems, such as the product spoken with a lisp, typically carries out that treatment or prolonged exercise, taking medicine is improved by operation.Training
There are many instruments of pronunciation, such as: Speech rehabilitation training system, verbal language comprehensive training system, early stage language assessment and training
System, the mechanical equipments such as aphasis diagnosis and therapy apparatus;Therefore existing solution just has following deficiency: 1. is expensive, and one is whole
Set process gets off and 10 to 20 ten thousand yuan can be spent to differ according to the severity of the state of an illness, and success rate is very low;2. drug can bring secondary work
With;3. bringing psychological pressure to patient;4. whether can normal speech be a low probability event;5. can spend much more very
Between (remembered as unit of year) and energy;6. mechanical volume is big, weight is heavy, expensive, it cannot carry, use at any time
(generally all hospital just has).Namely have that expensive, success rate is low;It wastes time and energy, is brought to patient huge
Psychological pressure;The problems such as mechanical volume is big, weight is heavy, expensive, and portability is poor.
In conclusion problem of the existing technology is:
(1) expensive, success rate is very low;Drug can bring side effect, bring psychological pressure to patient, spend very more
Time and efforts.
(2) mechanical volume is big, weight is heavy, expensive, cannot carry, use at any time.
Solve the difficulty and meaning of above-mentioned technical problem:The receipts of pronunciation data are carried out using " intelligence learning " module of APP
Collection;The audio file of user is collected using big data, the data of magnanimity, which are provided to server end, carries out machine learning,
This accuracy for identifying further raising equipment to fuzzy phoneme.Improve user experience.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of adjoint cerebral palsies to speak with a lisp supplementary controlled system
And method, assistor.
The invention is realized in this way a kind of adjoint cerebral palsy speaks with a lisp supplementary controlled system, the adjoint cerebral palsy
Speaking with a lisp supplementary controlled system includes:
Client: for acquiring the audio data file of patient's pronunciation and playing the sound after repairing;
Server end: connecting with client, for the corresponding text file of client to be carried out machine learning, forms one
Identification model when patient talks, identifies the specific location which pronunciation needs to be replaced and be replaced by this model, then
The model is issued to client.
Further, the server end further include: API service unit, machine learning unit, Database Unit
API service unit: client and server-side can be allowed to obtain the service unit of data connection.
Machine learning: by the audio data file and corresponding text text of collected patient's pronunciation on the client
Part carries out machine learning in server end together, by will form the fuzzy phoneme that can identify that needs replace after machine learning
Specific location and be specifically " identification model " which sound needs to replace.Then this model is issued to client.
Database Unit: for storing trained text, user basic information, user's fuzzy phoneme data, standard pronunciation data, machine
The data such as the identification model generated after device study.
Further, the client further include: training unit, recognition unit, replacement broadcast unit.
Training unit: patient to user pronunciation data collection, is housed very by the intelligence learning module of APP in this module
More texts contain in the sound that patient can not issue or the sound that pronunciation obscures and life often in the pronunciation of these texts
Sound is read aloud the text in this module by patient and is collected to patient's pronunciation data, the pronunciation audio that will be collected into
File and the text that is corresponding to it are sent collectively to server end and carry out machine learning.
Recognition unit: by the identification model that server issues identify specifically which pronunciation need replace repairing and its
Next specific location can obscure pronunciation by replacing the program replacement repairing of broadcast unit.
Replacement broadcast unit: the function of replacing broadcast unit is realized by executing code module,
After receiving the relevant information that the needs that recognition unit is sent replace repairing, executing code can be transferred in standard audio library
Corresponding standard audio goes to corresponding position to be replaced repairing, then is played back the sound after repairing completely by loudspeaker.
A kind of application adjoint cerebral palsy that is to provide of an object of the present invention speaks with a lisp supplementary controlled system
Adjoint cerebral palsy speak with a lisp auxiliary control method, the adjoint cerebral palsy speaks with a lisp auxiliary control method and includes:
Step 1 acquires the audio data file of patient's pronunciation, together by corresponding text file on the client
It is submitted to server end and carries out machine learning, form an identification model, when patient talks, identify which pronunciation needs to be replaced
Then the model is issued to client by the specific location for changing and being replaced;
Step 2, the information that client-side program is provided according to identification model, the sound that user can not be issued or
The fuzzy phoneme of sending is replaced repairing with standard pronunciation, then is played back the sound after repairing completely by loudspeaker.
The audio data file of " intelligence learning " module acquisition patient's pronunciation on the client, by corresponding text
File is submitted to server end together and carries out machine learning, forms one " identification model ", model is issued to client;
When patient is using assistor exchange is spoken with a lisp with property brain paralysis, system can be automatically by " identification model " intelligence
Will be identified without the sound of sending or the fuzzy phoneme of sending, then by need replace repairing specific location and tool
Which is sent to another execution code module to body;
After execution code module receives relevant information, it will can need to replace corresponding in the local transfer standard audio library of repairing
Standard audio go to be replaced repairing, then by loudspeaker by repair it is complete after sound play back.
A kind of use adjoint cerebral palsy that is to provide of the second object of the present invention speaks with a lisp supplementary controlled system
Adjoint cerebral palsy speak with a lisp assistor, it includes: microphone, audio transmission that the adjoint cerebral palsy, which speaks with a lisp assistor,
Line, loudspeaker, mobile phone;
Microphone and loudspeaker are connect by audio transmission line with mobile phone.
Supplementary controlled system is spoken with a lisp using the adjoint cerebral palsy another object of the present invention is to provide a kind of
Information data processing terminal.
In conclusion advantages of the present invention and good effect are as follows:The present invention reduces cost;Any side effect will not be brought;
Voice restoration is accurate, immediately, significant effect, can use at any time;Small product size structure is small, has achieved the effect that stealth, uses
In the process psychological pressure will not be brought to patient;Product weight is light, can be carried around and uses at any time;User is not needed to spend greatly
The time and efforts of amount.Product significant effect of the invention and it is cheap, can effectively help those that cannot bear operation
Or the people of the high expense of speech rehabilitation training;The crowd for making pronunciation fuzzy has other other than performing the operation and speech rehabilitation is trained
Selection;It is compared with operation, speech rehabilitation training, the voice restoration of this product has accomplished instantaneity, and it is a large amount of to have saved patient
Time can be used as a auxiliary tool of operation or speech rehabilitation training.
Currently, there is no such a direct helps, and there is the crowd of disfluency to solve the problems, such as to speak with a lisp on the market
Product, be all to carry out treatment or prolonged exercise by operation to be improved, so to can be used as patient flat for product of the invention
When a auxiliary product that is exchanged with other people.Fuzzy pronunciation audio data and the corresponding standard of user are acquired by microphone
Sound text data gives machine learning, and the model of a fuzzy pronunciation of replacement repairing is formed by machine learning, thus intelligence
The fuzzy phoneme of sound or sending that user can not issue is replaced repairing with standard pronunciation, it at this moment again will by loudspeaker
Sound after repairing is complete plays back.The present invention reduces cost (hardware cost is differed according to quality 30 to 100);It will not band
Carry out any side effect;Voice restoration is accurate, immediately, significant effect, can use at any time;Small product size structure is small, has reached hidden
The effect of shape will not bring psychological pressure to patient in use process;Product weight is light, can be carried around and uses at any time;It is not required to
User is wanted to expend considerable time and effort;Reduce the economic pressures of patient home.Product significant effect and it is cheap, can
Effectively to help to those not do the people of operation or rehabilitation training;The crowd for making pronunciation fuzzy have in addition to perform the operation and train with
Other outer selections;It is compared with operation, training, the voice restoration of product has accomplished instantaneity, validity, and it is big to have saved patient
The time and efforts of amount;It can be used as a auxiliary tool of operation or training;User is avoided to be corrected pronunciation mistakes and a large amount of rehabilitations
Trained pain.
Large medical equipment | Paste sound is lived again device |
Pure Medical Devices | For public good |
Treatment | The language reparation of outer criticality |
Success rate is uncertain | Effect is obvious |
Treatment needs the time | Instantaneity |
It takes medicine while treatment | Without drug side-effect |
Volume is big, not Portable belt | It is mini portable |
It is expensive | Price material benefit |
Nothing | Accuracy is repaired in APP pronunciation exercises, enhancing |
Detailed description of the invention
Fig. 1 is that adjoint cerebral palsy provided in an embodiment of the present invention speaks with a lisp supplementary controlled system structural schematic diagram;
Fig. 2 is that adjoint cerebral palsy provided in an embodiment of the present invention speaks with a lisp auxiliary control method flow chart;
Fig. 3 is that adjoint cerebral palsy provided in an embodiment of the present invention speaks with a lisp assistant structure schematic diagram;
In figure: 1, client;1-1, training unit;1-2, recognition unit;1-3, replacement broadcast unit;2, server end;
2-1, API service unit;2-2, machine learning unit;2-3, Database Unit;3, microphone;4, audio transmission line;5, loudspeaking
Device;6, mobile phone.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to
Limit the present invention.
Product significant effect of the invention and it is cheap, can effectively help those that cannot bear operation or speech health
The people of high expense is practiced in refreshment;The crowd for making pronunciation fuzzy has other selections other than performing the operation and speech rehabilitation is trained;With
Operation, speech rehabilitation training are compared, and the voice restoration of this product has accomplished instantaneity, and having saved patient's a large amount of time can be with
A auxiliary tool as operation or speech rehabilitation training.
Application principle of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, it includes: client that adjoint cerebral palsy provided in an embodiment of the present invention, which speaks with a lisp supplementary controlled system,
1, server end 2.
Client 1, for acquiring the audio data file of patient's pronunciation.
Server end 2 is connect with client 1, for the corresponding text file of client 1 to be carried out machine learning, is formed
The model is issued to client 1 by one identification model.
Client 1 further include: training unit 1-1, recognition unit 1-2, replacement broadcast unit 1-3.
Server end 2 further include: API service unit 2-1, machine learning unit 2-2, Database Unit 2-3.
As shown in Fig. 2, adjoint cerebral palsy provided in an embodiment of the present invention speaks with a lisp auxiliary control method includes:
S201: the audio data file of patient's pronunciation is acquired on the client, corresponding text file is mentioned together
It is sent to server end and carries out machine learning, form an identification model, which is issued to client;
S202: accurate, intelligence replaces the fuzzy phoneme of sound or sending that user can not issue with standard pronunciation
Repair is mended, then is played back the sound after repairing completely by loudspeaker.
As shown in figure 3, it includes: microphone 3, audio that adjoint cerebral palsy provided in an embodiment of the present invention, which speaks with a lisp assistor,
Transmission line 4, loudspeaker 5, mobile phone 6.
Microphone 3 and loudspeaker 5 are connect by audio transmission line 4 with mobile phone 6.
The application method that adjoint cerebral palsy provided in an embodiment of the present invention speaks with a lisp assistor includes:
User connects hardware device in mobile phone cochain, and the module on APP is selected to can be used.When being exchanged with other people, when repairing
When sound after multiple needs outer put, a conversion line link microphone, loudspeaker and mobile phone are utilized;Sound after reparation is not required to
When putting outside, then mobile phone directly is linked with earphone.
1, open APP, be inserted into hardware device, click " beginning ", start to talk, sound is automatically repaired, clearly sound with
Play;
2, APP is opened, is clicked " closing ", terminates pronunciation and repairs, terminates pronunciation repair function;
3, APP is opened, is clicked " intelligence learning ", is clicked " BEGIN ", pronunciation exercises are started, clicks " STOP ", retracts main boundary
Face;
4, APP is opened, " quick to introduce " is clicked, or clicks " quick greeting ", plays quick voice;
5, APP is opened, is clicked " about us ", can check our team and product introduction.
Application effect of the invention is described in detail below with reference to experiment.
Audio shearing replacement
Replace starting point: the first articulation point of each word of pronunciation is starting point (can find this starting point by machine learning)
Replace length: 0.1s
Since people say that the time of a word is far longer than 0.1s, even if in the sound of dysarthrosis person that it is every
The pronunciation of a word is replaced 0.1 second, what difference is received not listen in range in human ear, or it can be said that even if hear
Some differences of sound be also it is acceptable, said for what compared to dysarthrosis person can not be caught completely before, at present
Repairing effect be good.
The pronunciation starting point of each word will be replaced 0.1 second, and 20 words are shared in above a segment of audio,
That is replacement duration=0.1*20=2s (audio for being substituted 14%) altogether
It is found through experiments that audio ratio that almost every a segment of audio is replaced all 15% or so, floats up and down 2% not
It is fixed.
The fuzzy phoneme of dysarthrosis person 14% is substituted in the receptible tone color error range of human ear, improves at the same time
The sound articulation of dysarthrosis person can be increased to by the clarity of his sound according to experiment estimation from 40% at present
80%.
Machine learning:
Machine Learning Theory be mainly design and analyze it is some allow computer can automatic " study " algorithm.Machine learning
Algorithm is that a kind of automatically analyze from data obtains rule, and the algorithm that assimilated equations predict unknown data.Study is
One complicated intelligency activity, learning process and reasoning process be it is closely coupled, according to used in study reasoning number, machine
Strategy used by device learns can be generally divided into 4 kinds --- rote learning, by teaching study, analogical learning and passing through example
Study.Reasoning used in study is more, and the ability of system is stronger.
And product is just needing machine learning analysis data to obtain rule, to the function of unknown data prediction, will constantly provide
A large amount of patients obscure voice, carry out machine learning, eventually find the place of obvious pronunciation characteristic, that is, need to replace audio
Place
It plays: using common Android or apple playing function, played back by loudspeaker.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (5)
1. a kind of adjoint cerebral palsy speaks with a lisp supplementary controlled system, which is characterized in that the adjoint cerebral palsy speaks with a lisp auxiliary
The control system is helped to include:
Client: for acquiring the audio data file of patient's pronunciation;
Server end: connecting with client, for the corresponding text file of client to be carried out machine learning, forms an identification
Model when patient talks, identifies the specific location which pronunciation needs to be replaced and be replaced, is then issued to the model
Client.
2. as described in claim 1 speak with a lisp supplementary controlled system with cerebral palsy, which is characterized in that the server end
Further include: API service unit, machine learning unit, Database Unit.
3. a kind of speak with a lisp using described in claim 1 with the adjoint cerebral palsy that cerebral palsy speaks with a lisp supplementary controlled system
Auxiliary control method, which is characterized in that the adjoint cerebral palsy speaks with a lisp auxiliary control method and includes:
Step 1: the audio data file of patient's pronunciation is acquired on the client, corresponding text file is submitted together
Machine learning is carried out to server end, to form which an identification model can recognize that by this model when patient talks
The specific location that a little pronunciations need to be replaced and be replaced, is then issued to client for the model;
Step 2: the information that client-side program is provided according to identification model, the sound that user can not be issued or sending
Fuzzy phoneme be replaced repairing with standard pronunciation, then by loudspeaker by repair it is complete after sound play back.
4. a kind of speak with a lisp using described in claim 1 with the adjoint cerebral palsy that cerebral palsy speaks with a lisp supplementary controlled system
Assistor, which is characterized in that the adjoint cerebral palsy speak with a lisp assistor include: microphone, audio transmission line, loudspeaker,
Cell phone application;
Microphone and loudspeaker are connect by audio transmission line with mobile phone.
5. a kind of using the Information Number for speaking with a lisp supplementary controlled system described in claims 1 to 3 any one with cerebral palsy
According to processing terminal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810939343.2A CN109064789A (en) | 2018-08-17 | 2018-08-17 | A kind of adjoint cerebral palsy speaks with a lisp supplementary controlled system and method, assistor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810939343.2A CN109064789A (en) | 2018-08-17 | 2018-08-17 | A kind of adjoint cerebral palsy speaks with a lisp supplementary controlled system and method, assistor |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109064789A true CN109064789A (en) | 2018-12-21 |
Family
ID=64687154
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810939343.2A Pending CN109064789A (en) | 2018-08-17 | 2018-08-17 | A kind of adjoint cerebral palsy speaks with a lisp supplementary controlled system and method, assistor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109064789A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110415678A (en) * | 2019-06-13 | 2019-11-05 | 百度时代网络技术(北京)有限公司 | Customized voice broadcast client, server, system and method |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012049368A1 (en) * | 2010-10-12 | 2012-04-19 | Pronouncer Europe Oy | Method of linguistic profiling |
CN103310666A (en) * | 2013-05-24 | 2013-09-18 | 深圳市九洲电器有限公司 | Language learning device |
CN103474067A (en) * | 2013-08-19 | 2013-12-25 | 安徽科大讯飞信息科技股份有限公司 | Voice signal transmission method and system |
CN105185372A (en) * | 2015-10-20 | 2015-12-23 | 百度在线网络技术(北京)有限公司 | Training method for multiple personalized acoustic models, and voice synthesis method and voice synthesis device |
CN105551328A (en) * | 2016-01-28 | 2016-05-04 | 北京聚力互信教育科技有限公司 | Language teaching coaching and study synchronization integration system on the basis of mobile interaction and big data analysis |
CN105810205A (en) * | 2014-12-29 | 2016-07-27 | ***通信集团公司 | Speech processing method and device |
CN106683677A (en) * | 2015-11-06 | 2017-05-17 | 阿里巴巴集团控股有限公司 | Method and device for recognizing voice |
CN107301863A (en) * | 2017-07-13 | 2017-10-27 | 江苏师范大学 | A kind of deaf-mute child's disfluency method of rehabilitation and rehabilitation training system |
CN107993653A (en) * | 2017-11-30 | 2018-05-04 | 南京云游智能科技有限公司 | The incorrect pronunciations of speech recognition apparatus correct update method and more new system automatically |
-
2018
- 2018-08-17 CN CN201810939343.2A patent/CN109064789A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012049368A1 (en) * | 2010-10-12 | 2012-04-19 | Pronouncer Europe Oy | Method of linguistic profiling |
CN103310666A (en) * | 2013-05-24 | 2013-09-18 | 深圳市九洲电器有限公司 | Language learning device |
CN103474067A (en) * | 2013-08-19 | 2013-12-25 | 安徽科大讯飞信息科技股份有限公司 | Voice signal transmission method and system |
CN105810205A (en) * | 2014-12-29 | 2016-07-27 | ***通信集团公司 | Speech processing method and device |
CN105185372A (en) * | 2015-10-20 | 2015-12-23 | 百度在线网络技术(北京)有限公司 | Training method for multiple personalized acoustic models, and voice synthesis method and voice synthesis device |
CN106683677A (en) * | 2015-11-06 | 2017-05-17 | 阿里巴巴集团控股有限公司 | Method and device for recognizing voice |
CN105551328A (en) * | 2016-01-28 | 2016-05-04 | 北京聚力互信教育科技有限公司 | Language teaching coaching and study synchronization integration system on the basis of mobile interaction and big data analysis |
CN107301863A (en) * | 2017-07-13 | 2017-10-27 | 江苏师范大学 | A kind of deaf-mute child's disfluency method of rehabilitation and rehabilitation training system |
CN107993653A (en) * | 2017-11-30 | 2018-05-04 | 南京云游智能科技有限公司 | The incorrect pronunciations of speech recognition apparatus correct update method and more new system automatically |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110415678A (en) * | 2019-06-13 | 2019-11-05 | 百度时代网络技术(北京)有限公司 | Customized voice broadcast client, server, system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Geers | Factors affecting the development of speech, language, and literacy in children with early cochlear implantation | |
Szagun et al. | Sources of variability in language development of children with cochlear implants: Age at implantation, parental language, and early features of children's language construction | |
Kaplan et al. | Early-deafened adult cochlear implant users: assessment of outcomes. | |
Rufsvold | The impact of language input on deaf and hard-of-hearing preschool children who use listening and spoken language | |
CN107562911A (en) | More wheel interaction probabilistic model training methods and auto-answer method | |
de Wet et al. | Automatic assessment of oral language proficiency and listening comprehension | |
Wu et al. | Oral English Speech Recognition Based on Enhanced Temporal Convolutional Network. | |
EP4064289A1 (en) | Method and device for determining psychological counseling training scheme | |
KR20200113143A (en) | A calibration system for language learner by using audio information and voice recognition result | |
CN109064789A (en) | A kind of adjoint cerebral palsy speaks with a lisp supplementary controlled system and method, assistor | |
CN110689770A (en) | Online classroom voice transcription and translation system and working method thereof | |
Rose et al. | A comparison of verbal and gesture treatments for a word production deficit resulting from acquired apraxia of speech | |
Prince | Writing it down: Issues relating to the use of restitution tasks in listening comprehension | |
Tamati et al. | The perception of foreign-accented speech by cochlear implant users. | |
CN115062628A (en) | Automatic simulation method for doctor-patient communication conversation based on knowledge graph | |
Zhao | Speech-recognition technology in health care and special-needs assistance [Life Sciences] | |
Hird et al. | Facilitating use of speech recognition software for people with disabilities: A comparison of three treatments | |
JP2015060056A (en) | Education device and ic and medium for education device | |
CN110767282B (en) | Health record generation method and device and computer readable storage medium | |
KR20220140301A (en) | Video learning systems for enable learners to be identified through artificial intelligence and method thereof | |
Jamis et al. | Speak app: A development of mobile application guide for filipino people with motor speech disorder | |
KR101765880B1 (en) | Language study game system and method using a ball input device | |
Tran | Mobile learning and speech technology for language teachers’ professional development: A design-based study | |
Madina et al. | Evaluation of STT Technology Performance for Spanish Dysarthric Speech: Description of a Pilot Experiment | |
CN108897731A (en) | Oral English Practice learning method and system |
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 |
Application publication date: 20181221 |
|
RJ01 | Rejection of invention patent application after publication |