CN113286243A - Error correction system and method for self-testing speech recognition - Google Patents
Error correction system and method for self-testing speech recognition Download PDFInfo
- Publication number
- CN113286243A CN113286243A CN202110477821.4A CN202110477821A CN113286243A CN 113286243 A CN113286243 A CN 113286243A CN 202110477821 A CN202110477821 A CN 202110477821A CN 113286243 A CN113286243 A CN 113286243A
- Authority
- CN
- China
- Prior art keywords
- speech
- voice
- processing unit
- consonants
- vowels
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000012937 correction Methods 0.000 title claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 26
- 230000033228 biological regulation Effects 0.000 claims abstract description 20
- 238000001228 spectrum Methods 0.000 claims abstract description 20
- 238000010183 spectrum analysis Methods 0.000 claims description 13
- 230000003595 spectral effect Effects 0.000 claims description 8
- 230000004044 response Effects 0.000 claims description 4
- 206010011878 Deafness Diseases 0.000 claims description 3
- 230000007812 deficiency Effects 0.000 claims description 3
- 230000010370 hearing loss Effects 0.000 claims description 3
- 231100000888 hearing loss Toxicity 0.000 claims description 3
- 208000016354 hearing loss disease Diseases 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000012076 audiometry Methods 0.000 abstract description 17
- 230000009123 feedback regulation Effects 0.000 abstract description 3
- 235000008429 bread Nutrition 0.000 description 5
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R25/00—Deaf-aid sets, i.e. electro-acoustic or electro-mechanical hearing aids; Electric tinnitus maskers providing an auditory perception
- H04R25/50—Customised settings for obtaining desired overall acoustical characteristics
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
- G10L19/008—Multichannel audio signal coding or decoding using interchannel correlation to reduce redundancy, e.g. joint-stereo, intensity-coding or matrixing
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
- G10L19/02—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using spectral analysis, e.g. transform vocoders or subband vocoders
- G10L19/0204—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using spectral analysis, e.g. transform vocoders or subband vocoders using subband decomposition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
- G10L19/02—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using spectral analysis, e.g. transform vocoders or subband vocoders
- G10L19/0204—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using spectral analysis, e.g. transform vocoders or subband vocoders using subband decomposition
- G10L19/0208—Subband vocoders
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2225/00—Details of deaf aids covered by H04R25/00, not provided for in any of its subgroups
- H04R2225/43—Signal processing in hearing aids to enhance the speech intelligibility
Abstract
The invention discloses an error correction system and method for self-testing speech recognition, which comprises a processing unit, a display screen and a multi-channel coding earphone, wherein the display screen can display a speech signal, the coding earphone can play the speech signal, the processing unit can perform frequency spectrum presentation and coding regulation and control on vowels and consonants in the speech signal, an automatic feedback regulation and control path for speech detail testing and coding regulation and control is established, fine speech audiometry is performed in a narrower frequency range, further, the detailed characteristics of speech recognition of a subject are found, speech recognition errors are found, and a speech pronunciation waveform is changed, so that the speech recognition degree and the speech definition are improved, the speech audiometry accuracy is improved, and the fitting satisfaction degree of a hearing aid is improved.
Description
Technical Field
The invention relates to the technical field of medical equipment, in particular to an error correction system and method for self-testing speech recognition.
Background
Current speech audiometry equipment only tests and records "clearly audible" test signals, and does not perform error correction testing on "clearly audible" test signals.
The existing speech audiometry method is to provide test speech signals with certain sound intensity level, so that a subject can recognize the signals to obtain a speech recognition threshold, calculate the proportion of the accurately recognizable speech signals to the total number of the played speech signals, and obtain data such as speech recognition rate and the like, which are used for judging the degree of the subject recognizing the speech signals or judging the speech recognition improvement degree after using a hearing aid, for example, some characters or words can be recognized (clearly heard) and some characters and words can not be recognized (not heard), but we do not know what sound the subject can hear at all? What has changed after the test words entered the subject's auditory system? For example, in conventional speech audiometry, the initial audiometry gives a test signal of "bread", and the subject may not hear the "bread", but may recognize the "bag", and the two words of "bread" cannot be completely repeated, so that the audiometry result is deviated.
On the other hand, in the prior art, all hearing aid testing and matching methods are that a testing and matching operator adjusts parameters of the hearing aid according to feedback information of a user or adjusts sound pressure output by the hearing aid by using a real ear testing device, and the problems of speech recognition and speech definition cannot be solved in the methods. For example, it is difficult for the hearing aid user to accurately describe the form of the sound being heard, and for the dispenser to understand the user's circumstances, with large errors between the two.
Disclosure of Invention
The invention aims to provide an error correction system and method for self-test speech recognition, which can decompose speech into syllables, perform spectrum analysis and coding regulation and control on the syllables, realize detail test and coding regulation and control, perform fine audiometry in a narrower frequency range, further discover detail characteristics and improve speech sound recognition and speech definition.
In order to achieve the purpose, the invention adopts the following technical scheme:
an error correction system for self-test speech recognition comprises a processing unit, a display screen and a multi-channel coding earphone;
the display screen can display voice signals, and meanwhile, a subject can make a 'hearing clear' or 'hearing unclear' judgment on the voice signals to respond by clicking 'hearing clear' or 'hearing unclear' keys;
the multichannel coding earphone can process and play voice signals through a plurality of channels, and each channel of the multichannel coding earphone is independently controlled to make up 'hearing deficiency' of a subject with hearing loss;
the processing unit can perform spectrum coding regulation and control on vowels and consonants in the voice signals which are judged to be inaudible by the testee, and perform speech recognition test again through the multi-channel coding earphone.
Therefore, the display screen and the hearing aid can simultaneously play and display corresponding voice signals, the voice signals can comprise voice and text information such as single tone, single character, word, single sentence, paragraph and the like, when a subject hears inconsistency between voice and the display screen or deviation or inaudibility exists, the processing unit can perform spectrum presentation and coding regulation and control on vowel and consonant in the voice signals, an automatic feedback regulation and control path of voice detail testing and coding regulation and control is set up, fine speech audiometry is performed in a narrower frequency range, further details of speech recognition of the subject are found, errors of voice recognition are found, voice pronunciation waveforms are changed, speech recognition degree and voice definition are improved, speech audiometry accuracy is improved, hearing aid fitting satisfaction is improved, and the problem that the speech recognition degree and the speech definition degree are lower is solved.
In some embodiments, the processing unit includes a speech signal memory capable of storing the speech signal and the vowel and consonant audio files and text for each test speech.
Therefore, the voice signal memory stores voice signals comprising audio file characters such as vowels and consonants in the voice signal expression, and can be in data connection with the multi-channel coding earphone and the display screen; the voice signal memory also stores syllable frequency component data after voice spectrum analysis and syllable coding data after regulation and control of the voice spectrum coder.
In some embodiments, the processing unit further comprises a voice playing controller, the voice playing controller can control the playing speed of the voice signal according to the syllable composition of the voice, meanwhile, the display screen can display the vowel and the consonant of the text corresponding to the voice, and the subject can control the playing of the vowel and the consonant by clicking the text.
In some embodiments, the processing unit further comprises a speech spectral encoder capable of performing spectral analysis on the decomposed syllable, and the display screen displays a spectral waveform of the speech and a waveform of the speech after encoding.
In some embodiments, the speech spectrum encoder is further capable of performing multi-band division on the spectrum of the spectrally analyzed vowel and consonant, and adjusting and controlling the gain in each frequency band to correspond to the channel bandwidth of the multi-channel coding headphone.
Therefore, the voice spectrum encoder can perform multi-band division and regulation on the syllables, so that the syllables are regulated and controlled in detail, and the recognition degree and the definition of the user on the voice are improved.
In some embodiments, the display screen may be a touch screen, and the processing unit may be plug-in to connect with the computer.
An error correction method for self-test speech recognition comprises the following steps:
decomposing the speech signal with the wrong recognition into syllables, and performing frequency band division and multi-channel coding regulation and control on the spectrum waveforms of the vowels and the consonants in the speech.
In some embodiments, the method comprises the steps of:
s1: the hearing aid and the display screen respectively play and display corresponding voice signals synchronously;
s2: if the played voice corresponds to the voice characters in the display screen and is confirmed to be 'heard clearly' by the subject through 'clicking', playing the next voice signal; if the played and displayed voice signal is clicked to be 'inaudible', judging that the voice signal is identified wrongly;
s3: the processing unit automatically and independently plays vowel and consonant signals in the speech signals with the errors in recognition;
s4: performing spectrum analysis on unidentifiable vowels and consonants, and presenting vowel and consonant waveforms comprising a plurality of frequency bands;
s5: carrying out encoding regulation and control of loudness gain or attenuation on vowels and consonants after the frequency spectrum analysis, changing frequency response characteristics, playing and then identifying;
s6: after encoding, the part of the "inaudible" speech is changed to "hear clearly", and the speech signal memory records this difference and can derive it as reference data for the fine fitting of the hearing aid.
The invention has the beneficial effects that: the system can perform frequency spectrum presentation and coding regulation and control on vowels and consonants in the voice signals, build an automatic feedback regulation and control path of voice detail testing and coding regulation and control, perform fine speech audiometry in a narrower frequency range, further find the detailed characteristics of speech recognition of a subject, find speech recognition errors and change a speech pronunciation waveform, so that the speech recognition degree and the speech definition are improved, the speech audiometry accuracy is improved, and the fitting satisfaction degree of a hearing aid is improved.
Drawings
FIG. 1 is a block diagram of an error correction system for self-test speech recognition in accordance with the present invention;
FIG. 2 is a schematic diagram of a self-test speech recognition error correction system according to the present invention;
FIG. 3 is a flow chart of a method of error correction for self-test speech recognition in accordance with the present invention;
wherein: 1-a processing unit; 11-speech signal memory; 12-a voice play controller; 13-a speech spectral coder; 2-a display screen; 3-multichannel coding headphones.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
Referring to fig. 1 to 3, an error correction system for self-test speech recognition includes a processing unit 1, a display screen 2 and a multi-channel coding earphone 3;
the display screen 2 can display voice signals, and meanwhile, a subject can make a 'hearing clear' or 'hearing unclear' judgment on the voice signals to respond by clicking 'hearing clear' or 'hearing unclear' keys;
the multichannel coding earphone 3 can process and play voice signals through a plurality of channels, and each channel of the multichannel coding earphone 3 is independently controlled to make up for the 'hearing deficiency' of a subject with hearing loss;
the processing unit 1 can perform spectral coding regulation and control on vowels and consonants in the voice signals which are judged to be inaudible by the testee, and perform speech recognition test again through the multi-channel coding earphone 3.
To explain further, the processing unit 1 includes a voice signal memory 11, and the voice signal memory 11 can store the voice signal and the vowel and consonant audio files and text of each test voice.
Further, the processing unit 1 further includes a voice playing controller 12, the voice playing controller 12 can control the playing speed of the voice signal according to the syllable composition of the voice, meanwhile, the display screen 2 can display the vowel and consonant of the text corresponding to the voice, and the subject can control the playing of the vowel and consonant therein by "clicking" the text.
To explain further, the processing unit 1 further comprises a speech spectrum encoder 13, the speech spectrum encoder 13 is capable of performing a spectral analysis on the decomposed syllable, and the display 2 displays a spectral waveform of the speech and a waveform of the speech after encoding.
Further, the speech spectrum encoder 13 can perform multi-band division on the frequency spectrums of the vowels and consonants after the frequency spectrum analysis, and adjust and control the gain in each frequency band to correspond to the channel bandwidth of the multi-channel encoding earphone 3.
Further, the display screen 2 may be a touch screen, and the processing unit 1 may be connected to a computer in a hanging manner. The display screen 2 can display keys such as click, sound and unclear.
Further, the display screen 2 may be a touch screen, and the processing unit 1 may be connected to a computer in a hanging manner.
An error correction method for self-test speech recognition comprises the following steps:
decomposing the speech signal with the wrong recognition into syllables, and performing frequency band division and multi-channel coding regulation and control on the spectrum waveforms of the vowels and the consonants in the speech.
Further illustratively, the method comprises the steps of:
s1: the multi-channel coding earphone 3 and the display screen 2 respectively play and display corresponding voice signals synchronously;
s2: if the played voice corresponds to the voice characters in the display screen and is confirmed to be 'heard clearly' by the subject through 'clicking', playing the next voice signal; if the played and displayed voice signal is clicked to be 'inaudible', judging that the voice signal is identified wrongly;
s3: the processing unit 1 automatically and independently plays vowel and consonant signals in the speech signals with errors in recognition;
s4: performing spectrum analysis on unidentifiable vowels and consonants, and presenting vowel and consonant waveforms comprising a plurality of frequency bands;
s5: carrying out encoding regulation and control of loudness gain or attenuation on vowels and consonants after the frequency spectrum analysis, changing frequency response characteristics, playing and then identifying;
s6: after encoding, the part of the "inaudible" speech is changed to "hear clear", and the speech signal memory 11 records this difference and can derive it as reference data for the fine fitting of the hearing aid.
The working principle is as follows:
the speech recognition error correction system can regulate and control the syllables of the pronunciation, and improves speech recognition degree and definition of a user.
The display screen 2 and the multi-channel coding earphone 3 of the system can synchronously display and play corresponding voice signals, if a user can recognize and clearly listen to the voice signals, namely, the voice signals are consistent with what is heard, the system is judged to be correct in recognition, the next voice signal is played, and if the voice signals cannot be recognized or are not clearly heard, the system is judged to be wrong in recognition.
For example, "bread" two words, the user only hears "face" and can not hear "pack", or only hears "pack" and can not hear "face", or at least one of the words has deviation in pronunciation, resulting in unclear and unclear hearing, and is determined as "recognition error", then the voice playing controller 12 decomposes the two words of "bread" into pronunciation "mian bao", then into syllables "m-i-an b-ao", and plays each syllable again, the subject recognizes each syllable after decomposition to determine which specific syllables are not heard or are not heard and are identified as unrecognizable syllables, then the voice spectrum encoder 13 performs spectrum analysis on the unrecognizable syllables, analyzes the frequency components of the syllables, divides the frequency bands and presents vowel and consonant waveforms containing a plurality of frequency bands, and then the voice spectrum encoder 13 displays the auditory code of the syllable, the examinee adjusts and controls the loudness gain or attenuation of the auditory code of the syllable according to the frequency component of the syllable, changes the frequency response characteristic, plays the voice and identifies the voice, if the coded voice signal can be identified, the voice signal is changed into 'hearing clear', the voice signal memory 11 records the difference and can be educed to be used as the reference data for the fine fitting of the hearing aid, thereby the limitation that the existing speech audiometry only records the identifiable voice can be compensated, and the function of the speech audiometry equipment can be expanded.
Aiming at the 'unable recognition' or the 'inaudible' state of hearing aid fitting evaluation in speech audiometry, the system disclosed by the invention is utilized to carry out detail test and coding regulation and control, and fine audiometry is carried out in a narrower frequency range, so that detail characteristics are found, the speech audiometry accuracy is improved, and the hearing aid fitting satisfaction is improved.
The foregoing disclosure discloses only some embodiments of the invention. It will be apparent to those skilled in the art that various changes and modifications can be made without departing from the inventive concept herein, and it is intended to cover all such modifications and variations as fall within the scope of the invention.
Claims (8)
1. An error correction system for self-test speech recognition is characterized by comprising a processing unit (1), a display screen (2) and a multi-channel coding earphone (3);
the display screen (2) can display voice signals, and meanwhile, a subject can make a 'hear clearly' or 'hear unclearly' judgment on the voice signals to respond by clicking a 'hear clearly' or 'hear unclearly' button;
the multichannel coding earphone (3) can process and play the voice signals through a plurality of channels, and each channel of the multichannel coding earphone (3) is independently controlled to make up the 'hearing deficiency' of a subject with hearing loss;
the processing unit (1) can perform spectrum coding regulation and control on vowels and consonants in the voice signals which are judged to be inaudible by the testee, and performs speech recognition test again through the multi-channel coding earphone (3).
2. The error correction system for self-test speech recognition according to claim 1, wherein the processing unit (1) comprises a speech signal memory (11), the speech signal memory (11) being capable of storing speech signals and audio files and text for vowels and consonants of each test speech.
3. The system of claim 2, wherein the processing unit (1) further comprises a voice playing controller (12), the voice playing controller (12) can control the playing speed of the voice signal according to the syllable composition of the voice, meanwhile, the display screen (2) can display the vowels and consonants of the text corresponding to the voice, and the subject can control the playing of the vowels and consonants by clicking the text.
4. A system for error correction of self-test speech recognition according to claim 3, characterized in that the processing unit (1) further comprises a speech spectral encoder (13), the speech spectral encoder (13) is capable of performing spectral analysis of the decomposed syllables, and the display screen (2) displays the spectral waveform of the speech and the speech waveform after encoding.
5. The system according to claim 4, wherein the speech spectrum encoder (13) is further capable of performing multi-band division on the spectrum of the spectrally analyzed vowels and consonants, and adjusting the gain in each band to correspond to the channel bandwidth of the multi-channel encoding headphones (3).
6. The system of claim 1, wherein the display (2) is a touch screen, and the processing unit (1) is connected to a computer in a hanging manner.
7. An error correction method for self-test speech recognition comprises the following steps:
decomposing the speech signal with the wrong recognition into syllables, and performing frequency band division and multi-channel coding regulation and control on the spectrum waveforms of the vowels and the consonants in the speech.
8. The method of claim 7, wherein the method comprises the steps of:
s1: the multichannel coding earphone (3) and the display screen (2) respectively play and display corresponding voice signals synchronously;
s2: if the played voice corresponds to the voice characters in the display screen and is confirmed to be 'heard clearly' by the subject through 'clicking', playing the next voice signal; if the played and displayed voice signal is clicked to be 'inaudible', judging that the voice signal is identified wrongly;
s3: the processing unit (1) automatically and independently plays vowel and consonant signals in the speech signals with the errors in recognition;
s4: performing spectrum analysis on unidentifiable vowels and consonants, and presenting vowel and consonant waveforms comprising a plurality of frequency bands;
s5: carrying out encoding regulation and control of loudness gain or attenuation on vowels and consonants after the frequency spectrum analysis, changing frequency response characteristics, playing and then identifying;
s6: after encoding, the part of the "inaudible" speech is changed to "hear clear", and the speech signal memory (11) records this difference and can derive it as reference data for the fine fitting of the hearing aid.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110477821.4A CN113286243A (en) | 2021-04-29 | 2021-04-29 | Error correction system and method for self-testing speech recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110477821.4A CN113286243A (en) | 2021-04-29 | 2021-04-29 | Error correction system and method for self-testing speech recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113286243A true CN113286243A (en) | 2021-08-20 |
Family
ID=77277773
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110477821.4A Pending CN113286243A (en) | 2021-04-29 | 2021-04-29 | Error correction system and method for self-testing speech recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113286243A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1598927A (en) * | 2004-08-31 | 2005-03-23 | 四川微迪数字技术有限公司 | Chinese voice signal process method for digital deaf-aid |
CN101642399A (en) * | 2008-12-16 | 2010-02-10 | 中国科学院声学研究所 | Artificial cochlea speech processing method based on frequency modulation information and artificial cochlea speech processor |
CN102265335A (en) * | 2009-07-03 | 2011-11-30 | 松下电器产业株式会社 | Hearing aid adjustment device, method and program |
CN103054586A (en) * | 2012-12-17 | 2013-04-24 | 清华大学 | Chinese speech automatic audiometric method based on Chinese speech audiometric dynamic word list |
CN109246515A (en) * | 2018-10-09 | 2019-01-18 | 王青云 | A kind of intelligent earphone and method promoting personalized sound quality function |
CN111107478A (en) * | 2019-12-11 | 2020-05-05 | 江苏爱谛科技研究院有限公司 | Sound enhancement method and sound enhancement system |
CN111150934A (en) * | 2019-12-27 | 2020-05-15 | 重庆大学 | Evaluation system of Chinese tone coding strategy of cochlear implant |
CN111772641A (en) * | 2020-07-03 | 2020-10-16 | 佛山博智医疗科技有限公司 | Speech audiometric device and method |
CN112334057A (en) * | 2018-04-13 | 2021-02-05 | 康查耳公司 | Hearing assessment and configuration of hearing assistance devices |
-
2021
- 2021-04-29 CN CN202110477821.4A patent/CN113286243A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1598927A (en) * | 2004-08-31 | 2005-03-23 | 四川微迪数字技术有限公司 | Chinese voice signal process method for digital deaf-aid |
CN101642399A (en) * | 2008-12-16 | 2010-02-10 | 中国科学院声学研究所 | Artificial cochlea speech processing method based on frequency modulation information and artificial cochlea speech processor |
CN102265335A (en) * | 2009-07-03 | 2011-11-30 | 松下电器产业株式会社 | Hearing aid adjustment device, method and program |
CN103054586A (en) * | 2012-12-17 | 2013-04-24 | 清华大学 | Chinese speech automatic audiometric method based on Chinese speech audiometric dynamic word list |
CN112334057A (en) * | 2018-04-13 | 2021-02-05 | 康查耳公司 | Hearing assessment and configuration of hearing assistance devices |
CN109246515A (en) * | 2018-10-09 | 2019-01-18 | 王青云 | A kind of intelligent earphone and method promoting personalized sound quality function |
CN111107478A (en) * | 2019-12-11 | 2020-05-05 | 江苏爱谛科技研究院有限公司 | Sound enhancement method and sound enhancement system |
CN111150934A (en) * | 2019-12-27 | 2020-05-15 | 重庆大学 | Evaluation system of Chinese tone coding strategy of cochlear implant |
CN111772641A (en) * | 2020-07-03 | 2020-10-16 | 佛山博智医疗科技有限公司 | Speech audiometric device and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7206416B2 (en) | Speech-based optimization of digital hearing devices | |
Stevens et al. | Speaker authentication and identification: a comparison of spectrographic and auditory presentations of speech material | |
US9553984B2 (en) | Systems and methods for remotely tuning hearing devices | |
US20070286350A1 (en) | Speech-based optimization of digital hearing devices | |
Laures et al. | Perceptual effects of a flattened fundamental frequency at the sentence level under different listening conditions | |
WO2010117711A1 (en) | Systems and methods for tuning automatic speech recognition systems | |
US10334376B2 (en) | Hearing system with user-specific programming | |
KR20150104345A (en) | Voice synthesys apparatus and method for synthesizing voice | |
CN109378015B (en) | Voice learning system and method | |
de Vargas et al. | Haptic speech communication using stimuli evocative of phoneme production | |
WO2017008075A1 (en) | Systems and methods for human speech training | |
CN113286243A (en) | Error correction system and method for self-testing speech recognition | |
US20100056950A1 (en) | System and methods for creating reduced test sets used in assessing subject response to stimuli | |
SE517836C2 (en) | Method and apparatus for determining speech quality | |
Ganong | The selective adaptation effects of burst-cued stops | |
RU153322U1 (en) | DEVICE FOR TEACHING SPEAK (ORAL) SPEECH WITH VISUAL FEEDBACK | |
Derrick et al. | Aero-tactile integration in fricatives: Converting audio to air flow information for speech perception enhancement | |
Velmans | Speech Imitation in Simulated Deafness, Using Visual Cues and Recoded'Auditory Information | |
CN112565998A (en) | Fine adjustment device and application method thereof | |
Zekveld et al. | User evaluation of a communication system that automatically generates captions to improve telephone communication | |
Derrick et al. | Aero-tactile integration during speech perception: Effect of response and stimulus characteristics on syllable identification | |
Carney | Vibrotactile perception of segmental features of speech: A comparison of single-channel and multichannel instruments | |
Jacewicz | Listener sensitivity to variations in the relative amplitude of vowel formants | |
Mandel | Directly Comparing the Listening Strategies of Humans and Machines. | |
Allen | From Lord Rayleigh to Shannon: How do we decode speech? |
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: 20210820 |