CN109346058A - A kind of speech acoustics feature expansion system - Google Patents
A kind of speech acoustics feature expansion system Download PDFInfo
- Publication number
- CN109346058A CN109346058A CN201811443497.9A CN201811443497A CN109346058A CN 109346058 A CN109346058 A CN 109346058A CN 201811443497 A CN201811443497 A CN 201811443497A CN 109346058 A CN109346058 A CN 109346058A
- Authority
- CN
- China
- Prior art keywords
- voice
- submodule
- speech acoustics
- acoustics feature
- audio 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
- 238000012545 processing Methods 0.000 claims abstract description 48
- 238000001228 spectrum Methods 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000000926 separation method Methods 0.000 claims description 10
- 230000001360 synchronised effect Effects 0.000 claims description 4
- 210000004556 brain Anatomy 0.000 abstract description 22
- 238000000034 method Methods 0.000 abstract description 8
- 230000008447 perception Effects 0.000 abstract description 8
- 230000003321 amplification Effects 0.000 description 4
- 238000003199 nucleic acid amplification method Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000000214 mouth Anatomy 0.000 description 2
- 210000003928 nasal cavity Anatomy 0.000 description 2
- 210000000653 nervous system Anatomy 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000004936 stimulating effect Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 210000001260 vocal cord Anatomy 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000004641 brain development Effects 0.000 description 1
- 230000003930 cognitive ability Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000002610 neuroimaging Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
- G10L13/033—Voice editing, e.g. manipulating the voice of the synthesiser
-
- 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
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
- G10L13/027—Concept to speech synthesisers; Generation of natural phrases from machine-based concepts
-
- 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
- G10L15/24—Speech recognition using non-acoustical features
- G10L15/25—Speech recognition using non-acoustical features using position of the lips, movement of the lips or face analysis
-
- 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
-
- 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
- G10L25/18—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 spectral information of each sub-band
-
- 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
- G10L25/57—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 processing of video signals
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The application belongs to sound processing techniques field, expands system more particularly to a kind of speech acoustics feature.In Course of Language Learning, the corpus of suitable brain perception is produced after needing to expand speech acoustics feature for learner to stimulate brain.The application provides a kind of speech acoustics feature expansion system, including voice acquisition unit, the voice acquisition unit are connected with Audio Processing Unit, and the Audio Processing Unit is connected with video editing unit；Wherein, the voice acquisition unit, for being obtained to natural-sounding；The Audio Processing Unit, for carrying out different degrees of expansion to the spectrum signature in natural-sounding, to make corpus；The video editing unit is used for synthetic video segment after voice and video and processed voice edition.The speech acoustics feature, which expands system, can produce the corpus for being more suitable for brain perception, so that learner be helped to form the voice scope more close to mother tongue person in the brain.
Description
Technical field
The application belongs to sound processing techniques field, expands system more particularly to a kind of speech acoustics feature.
Background technique
With the rapid development of the related fieldss such as bioengineering, computer science, data statistics processing, brain imaging technique,
Brain science research combines the advantage of cross discipline, has carried out entirely to the interactive process of brain development growth and language learning environment
New exploration.Studies have shown that baby has just gradually lost the sensibility to non-mother tongue pronunciation after 12 months, to cause
Future foreign language phonetic study obstacle.One self-study a foreign language is often accustomed to going from oneself original speech perception
Recognize new language, so receive than very fast to the foreign language voice of similar mother tongue pronunciation, and to the voice not having in mother tongue, it connects
Being got up can be relatively difficult.However often when learning the voice similar with mother tongue, learner is easier to be influenced by mother tongue, from
And generate accent.For example, the U.S. has different perception from the brain of Chinese to a same English Phonetics.
Because insensitive to non-mother tongue pronunciation, learner is first from acoustically cannot comprehensively receiving language message, institute
To be difficult correctly to pronounce.Meanwhile learner's one phoneme of every study requires the voice scope for establishing this sound in the brain.
This voice scope not instead of point, a set.Because of the language ring that foreign language learner and mother tongue learner touch
Border is incomparable, so the voice scope established in their brains also greatly differs from each other.
In Course of Language Learning, suitable brain is produced for learner after the acoustic feature of natural-sounding is expanded
The corpus of perception, the nervous system for stimulating them to lose sensibility to non-mother tongue pronunciation reopen and then receive voice letter comprehensively
Breath, so that learner be helped to form the voice scope more close to mother tongue person in the brain.
Summary of the invention
1. technical problems to be solved
It produces based in Course of Language Learning, after the acoustic feature of natural-sounding is expanded for learner suitable
Language is reopened and then received comprehensively to the corpus of brain perception, the nervous system for stimulating them to lose sensibility to non-mother tongue pronunciation
Message breath, so that learner be helped to form the voice scope more close to mother tongue person in the brain, this application provides a kind of languages
Phonematics feature expands system.
2. technical solution
To achieve the above object, this application provides a kind of speech acoustics features to expand system, including voice obtains
Unit, the voice acquisition unit are connected with Audio Processing Unit, and the Audio Processing Unit is connected with video editing unit
It connects；
The voice acquisition unit, for being obtained to natural-sounding；
The Audio Processing Unit makes language for carrying out different degrees of expansion to the spectrum signature in natural-sounding
Material；
The video editing unit, for different video segment will to be synthesized after voice and video and processed voice edition.
Optionally, the Audio Processing Unit includes being based on MATLAB sound processing module.
Optionally, described based on MATLAB sound processing module includes that expand submodule, fundamental tone same for formant frequency difference
Walk the submodule that splices, frequency separation submodule, bandwidth separation submodule and gap separation submodule.
Optionally, the MATLAB sound processing module that is based on includes phonetic analysis submodule and sound synthon module.
Optionally, the video editing unit includes format analysis processing module and frame frequency processing module.
Optionally, the Audio Processing Unit, for carrying out 3 kinds of different degrees of expansions to the spectrum signature in voice,
Respectively 300%, 208%, 144%, to make corpus.
3. beneficial effect
Compared with prior art, the beneficial effect that a kind of speech acoustics feature provided by the present application expands system is:
Speech acoustics feature provided by the present application expands system, by by voice acquisition unit, Audio Processing Unit, video
Edit cell is connected；After expanding to the spectrum signature of natural-sounding, it is fabricated to video.It is connect when simulation pedology idiom speech
The acoustic feature of the voice contacted produces the corpus of suitable brain perception for learner to stimulate brain, makes its Foreign Language language
The decreased brain of sound susceptibility is capable of the physical acoustics feature of clearly perceptual speech, to establish in the brain similar female
The voice scope of language, and then improve the accuracy of pronunciation.
Detailed description of the invention
Fig. 1 is that a kind of speech acoustics feature of the application expands system principle schematic diagram；
In figure: 1- voice acquisition unit, 2- Audio Processing Unit, 3- video editing unit, 4- are based at MATLAB sound
Reason module, 5- formant frequency difference expand submodule, 6- pitch synchronous and splice submodule, 7- frequency separation submodule, 8- band
Width separation submodule, the gap 9- separate submodule, 10- phonetic analysis submodule, 11- sound rendering submodule, 12- format analysis processing
Module, 13- frame frequency processing module.
Specific embodiment
Hereinafter, specific embodiment of the reference attached drawing to the application is described in detail, it is detailed according to these
Description, one of ordinary skill in the art can implement the application it can be clearly understood that the application.Without prejudice to the application principle
In the case where, the feature in each different embodiment can be combined to obtain new embodiment, or be substituted certain
Certain features in embodiment, obtain other preferred embodiments.
The phonetic unit of " childrenese " by the vibration frequencies of vocal cords and oral cavity, cavum laryngis, nasal cavity resonant frequency by turgidly
It shows, the gap between the distinctive formant of vowel is also artificially increased.This exaggeration not only makes baby be easy to distinguish
Other phonetic unit, and the crucial phonetic feature that word senses are distinguished in mother tongue has been experienced simultaneously.When mother and child speak
Sound there is very big elasticity and mobility, such elasticity, which changes, to be facilitated baby and establishes effective acoustic mode to carry out
Voice is sorted out, that is, establishes the mother tongue pronunciation scope of each phoneme in the brain.Brain science field finds baby's acquistion
Mother tongue pronunciation process has following features: 1) baby has an opportunity to hear various people's one's voices in speech；2) they are organic can be appreciated that difference
The pronunciation degree of lip-rounding of people；3) sound when mother speaks to baby is total to by the vibration frequency of vocal cords and oral cavity, cavum laryngis, nasal cavity
Vibration frequency is turgidly showed.The highly beneficial energy for being conducive to improve difference phoneme of speech sound difference with baby of these three elements
Power establishes comprehensive mother tongue pronunciation scope.
Corpus, i.e. linguistic data.Corpus is the content of introduction on linguistics research.Corpus is the basic unit for constituting corpus.
Youngster is adult, the language used when especially mother speaks to infant to language (Matherese, or " mother's language ")
Speech.The content and form (words and phrases, intonation, word speed used etc.) of language all needs to adapt to the language competence and cognitive ability of children,
Consider the understanding and ability to accept of baby.Studies have shown that youngster has the physics expanded than normal speech to language in terms of voice
Acoustic feature.
Referring to Fig. 1, the application provides a kind of speech acoustics feature expansion system, including voice acquisition unit 1, the voice
Acquiring unit 1 is connected with Audio Processing Unit 2, and the Audio Processing Unit 2 is connected with video editing unit 3；
The voice acquisition unit 1, for being obtained to natural-sounding；
The Audio Processing Unit 2 makes language for carrying out different degrees of expansion to the spectrum signature in natural-sounding
Material；
The video editing unit 3, for different video segment will to be synthesized after voice and video and processed voice edition.
Optionally, the Audio Processing Unit 2 includes being based on MATLAB sound processing module 4.
Optionally, described that submodule 5, fundamental tone are expanded including formant frequency difference based on MATLAB sound processing module 4
Synchronize the submodule 6 that splices, frequency separation submodule 7, bandwidth separation submodule 8 and gap separation submodule 9.
Optionally, described that phonetic analysis submodule 10 and sound synthon mould are included based on MATLAB sound processing module 4
Block 11.Here it after the sound of 10 pairs of phonetic analysis submodule acquisitions is analyzed, is synthesized newly by sound rendering submodule 11
Sound.
Optionally, the video editing list 3 includes format analysis processing module 12 and frame frequency processing module 13.
Optionally, the Audio Processing Unit 2, for carrying out 3 kinds of different degrees of expansions to the spectrum signature in voice,
Respectively 300%, 208%, 144%, to make corpus.
Embodiment
Amplification target voice is to important differentiation acoustics element.For the voice of each group of needs training, need according to this
The distinctive elements of two speech acoustics features determine the physical parameter of specific natural sound processing.
Audio Processing Unit 2 is sent to after obtaining nature recording by voice acquisition unit 1, passes through MATLAB acoustic processing
Module 4 by sound spectrum signature carry out 3 kinds of different degrees of amplifications, respectively 300%, 208%, 144%, then with original
Beginning sound is made into the training corpus of four grades together.Such as English Phonetics/r-l/ pairs, 3 kinds of parameters are F3 cross frequence, F3 band
Wide, F3 transit time.In the synthesis process, 5 amplifications of submodule/r-l/ formant frequency is expanded by formant frequency difference
Difference simultaneously reduces F3 bandwidth.The amplification of/r-l/ time response is spliced son by pitch synchronous using time warping technique
Module 6 is added.English vowel/i-I/ pairs for another example passes through frequency separation submodule 7, bandwidth separates submodule 8 and gap
It separates submodule 9 and carries out the cross frequence of F1 and F2, bandwidth, adjust the gap between F1 and F2.
" the LPC Analysis and Synthesis of in MATLAB sound processing module 4 is used when production
This submodule of Speech ".LPC refers to Linear Prediction Coding.It is closed including phonetic analysis submodule 10 and sound
At submodule 11, it can analyze and synthesize new sound.(operation is shown in: DSP System ToolboxTMfunctionality
available at the command line.)
After acoustic processing, using Final Cut Pro7, including format analysis processing module 12 and frame frequency processing module 13,
Can mix and arrange in pairs or groups in time shaft different-format and frame frequency, and the slow motion that the video of sound passes through synchronous different editions is regarded
Frequency and time-stretching track, then put together with processed sound and are edited, synthesize different video segment, as into one
The corpus of step production training soft ware.
Speech acoustics feature provided by the present application expands system, by by voice acquisition unit, Audio Processing Unit, video
Edit cell is connected；After expanding to the spectrum signature of voice, it is fabricated to video.It is touched when simulation pedology idiom speech
Voice acoustic feature, produce the corpus of suitable brain perception for learner to stimulate brain, keep Foreign Language voice sensitive
The physical acoustics feature of clearly perceptual speech can be listened by spending decreased brain, establish the voice of similar mother tongue in the brain
Scope, and then improve the accuracy of pronunciation.
Although the application is described above by referring to specific embodiment, one of ordinary skill in the art are answered
Work as understanding, in principle disclosed in the present application and range, many modifications can be made for configuration disclosed in the present application and details.
The protection scope of the application is determined by the attached claims, and claim is intended to technical characteristic in claim
Equivalent literal meaning or range whole modifications for being included.
Claims (6)
1. a kind of speech acoustics feature expands system, it is characterised in that: including voice acquisition unit, the voice acquisition unit with
Audio Processing Unit is connected, and the Audio Processing Unit is connected with video editing unit；
The voice acquisition unit, for being obtained to natural-sounding；
The Audio Processing Unit makes corpus for carrying out different degrees of expansion to the spectrum signature in natural-sounding；
The video editing unit, for different video segment will to be synthesized after voice and video and processed voice edition.
2. speech acoustics feature as described in claim 1 expands system, it is characterised in that: the Audio Processing Unit includes base
In MATLAB sound processing module.
3. speech acoustics feature as claimed in claim 2 expands system, it is characterised in that: described to be based on MATLAB acoustic processing
Module includes that formant frequency difference expands submodule, pitch synchronous and splices submodule, frequency separation submodule, bandwidth segregant
Module and gap separate submodule.
4. speech acoustics feature as claimed in claim 2 expands system, it is characterised in that: described to be based on MATLAB acoustic processing
Module includes phonetic analysis submodule and sound synthon module.
5. speech acoustics feature as described in any one of claims 1 to 4 expands system, it is characterised in that: the video is compiled
Collecting unit includes format analysis processing module and frame frequency processing module.
6. speech acoustics feature as claimed in claim 5 expands system, it is characterised in that: the Audio Processing Unit is used for
To in voice spectrum signature carry out 3 kinds of different degrees of expansions, respectively 300%, 208%, 144%, to make corpus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811443497.9A CN109346058A (en) | 2018-11-29 | 2018-11-29 | A kind of speech acoustics feature expansion system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811443497.9A CN109346058A (en) | 2018-11-29 | 2018-11-29 | A kind of speech acoustics feature expansion system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109346058A true CN109346058A (en) | 2019-02-15 |
Family
ID=65319541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811443497.9A Pending CN109346058A (en) | 2018-11-29 | 2018-11-29 | A kind of speech acoustics feature expansion system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109346058A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0493980A (en) * | 1990-08-06 | 1992-03-26 | Takeshige Fujitani | Language learning system |
| CN1265217A (en) * | 1997-07-02 | 2000-08-30 | 西莫克国际有限公司 | Method and appts. for speech enhancement in speech communication system |
| WO2002056301A1 (en) * | 2001-01-12 | 2002-07-18 | Telefonaktiebolaget L M Ericsson (Publ) | Speech bandwidth extension |
| KR20030095474A (en) * | 2002-06-10 | 2003-12-24 | 휴먼씽크(주) | Method and apparatus for analysing a pitch, method and system for discriminating a corporal punishment, and computer readable medium storing a program thereof |
| CN1564245A (en) * | 2004-04-20 | 2005-01-12 | 上海上悦通讯技术有限公司 | Stunt method and device for baby's crying |
| CN1669074A (en) * | 2002-10-31 | 2005-09-14 | 富士通株式会社 | Voice intensifier |
| US20060149532A1 (en) * | 2004-12-31 | 2006-07-06 | Boillot Marc A | Method and apparatus for enhancing loudness of a speech signal |
| US20070168187A1 (en) * | 2006-01-13 | 2007-07-19 | Samuel Fletcher | Real time voice analysis and method for providing speech therapy |
| CN103827965A (en) * | 2011-07-29 | 2014-05-28 | Dts有限责任公司 | Adaptive voice intelligibility processor |
| CN105023574A (en) * | 2014-04-30 | 2015-11-04 | 安徽科大讯飞信息科技股份有限公司 | Method and system of enhancing TTS |
| CN105982641A (en) * | 2015-01-30 | 2016-10-05 | 上海泰亿格康复医疗科技股份有限公司 | Speech and language hypoacousie multi-parameter diagnosis and rehabilitation apparatus and cloud rehabilitation system |
| CN106710604A (en) * | 2016-12-07 | 2017-05-24 | 天津大学 | Formant enhancement apparatus and method for improving speech intelligibility |
| CN109378015A (en) * | 2018-11-29 | 2019-02-22 | 西安交通大学 | A kind of language learning system and method |
| CN209388698U (en) * | 2018-11-29 | 2019-09-13 | 西安交通大学 | A kind of speech acoustics feature expansion system |
-
2018
- 2018-11-29 CN CN201811443497.9A patent/CN109346058A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0493980A (en) * | 1990-08-06 | 1992-03-26 | Takeshige Fujitani | Language learning system |
| CN1265217A (en) * | 1997-07-02 | 2000-08-30 | 西莫克国际有限公司 | Method and appts. for speech enhancement in speech communication system |
| WO2002056301A1 (en) * | 2001-01-12 | 2002-07-18 | Telefonaktiebolaget L M Ericsson (Publ) | Speech bandwidth extension |
| KR20030095474A (en) * | 2002-06-10 | 2003-12-24 | 휴먼씽크(주) | Method and apparatus for analysing a pitch, method and system for discriminating a corporal punishment, and computer readable medium storing a program thereof |
| CN1669074A (en) * | 2002-10-31 | 2005-09-14 | 富士通株式会社 | Voice intensifier |
| CN1564245A (en) * | 2004-04-20 | 2005-01-12 | 上海上悦通讯技术有限公司 | Stunt method and device for baby's crying |
| US20060149532A1 (en) * | 2004-12-31 | 2006-07-06 | Boillot Marc A | Method and apparatus for enhancing loudness of a speech signal |
| US20070168187A1 (en) * | 2006-01-13 | 2007-07-19 | Samuel Fletcher | Real time voice analysis and method for providing speech therapy |
| CN103827965A (en) * | 2011-07-29 | 2014-05-28 | Dts有限责任公司 | Adaptive voice intelligibility processor |
| CN105023574A (en) * | 2014-04-30 | 2015-11-04 | 安徽科大讯飞信息科技股份有限公司 | Method and system of enhancing TTS |
| CN105982641A (en) * | 2015-01-30 | 2016-10-05 | 上海泰亿格康复医疗科技股份有限公司 | Speech and language hypoacousie multi-parameter diagnosis and rehabilitation apparatus and cloud rehabilitation system |
| CN106710604A (en) * | 2016-12-07 | 2017-05-24 | 天津大学 | Formant enhancement apparatus and method for improving speech intelligibility |
| CN109378015A (en) * | 2018-11-29 | 2019-02-22 | 西安交通大学 | A kind of language learning system and method |
| CN209388698U (en) * | 2018-11-29 | 2019-09-13 | 西安交通大学 | A kind of speech acoustics feature expansion system |
Non-Patent Citations (1)
| Title |
|---|
| 邓秀慧: "汉语数字耳语音识别研究", 电声技术, vol. 38, no. 7, 31 July 2014 (2014-07-31) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Escudero et al. | Spanish listeners’ perception of American and Southern British English vowels | |
| US20160365087A1 (en) | High end speech synthesis | |
| Remijsen | Tonal alignment is contrastive in falling contours in Dinka | |
| Tiwari et al. | Voice-How humans communicate? | |
| Burnham et al. | Perception of lexical tone across languages: Evidence for a linguistic mode of processing | |
| Taimi et al. | Children Learning a Non-native Vowel–The Effect of a Two-day Production Training. | |
| CN109378015B (en) | Voice learning system and method | |
| Lin et al. | End-to-end articulatory modeling for dysarthric articulatory attribute detection | |
| CN209388698U (en) | A kind of speech acoustics feature expansion system | |
| Zhang et al. | Adjustment of cue weighting in speech by speakers and listeners: Evidence from amplitude and duration modifications of Mandarin Chinese tone | |
| Sarvasy et al. | An acoustic analysis of Nungon vowels in child-versus adult-directed speech | |
| CN109346058A (en) | A kind of speech acoustics feature expansion system | |
| Fattoeva | phonetics as a branch of Linguistic | |
| CN209388701U (en) | A kind of language learning system | |
| Hakan et al. | Implementation of Turkish text-to-speech synthesis on a voice synthesizer card with prosodic features | |
| Petrushin et al. | Whispered speech prosody modeling for TTS synthesis | |
| Wong | Mothers do not enhance tonal contrasts in child-directed speech: Perceptual and acoustic evidence from child-directed Mandarin lexical tones | |
| Cibelli | The phonetic basis of a phonological pattern | |
| Sharma et al. | Recurrent neural network based approach to recognize assamese vowels using experimentally derived acoustic-phonetic features | |
| Keerio | Acoustic analysis of Sindhi speech-a precursor for an ASR system | |
| Feng et al. | The ability to use contextual cues to achieve phonological constancy emerges by 14 months. | |
| Mac et al. | Influences of speaker attitudes on glottalized tones: a study of two Vietnamese sentence-final particles | |
| Whalen et al. | Phonetics of endangered languages | |
| Hande | A review on speech synthesis an artificial voice production | |
| Butenko et al. | The Problem of Automatic Dialect Recognition |
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 |