CN109616122A - A kind of visualization hearing aid - Google Patents
A kind of visualization hearing aid Download PDFInfo
- Publication number
- CN109616122A CN109616122A CN201811567610.4A CN201811567610A CN109616122A CN 109616122 A CN109616122 A CN 109616122A CN 201811567610 A CN201811567610 A CN 201811567610A CN 109616122 A CN109616122 A CN 109616122A
- Authority
- CN
- China
- Prior art keywords
- voice
- text
- processing software
- voice signal
- sound
- 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
- 238000012800 visualization Methods 0.000 title description 3
- 230000004044 response Effects 0.000 claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 16
- 230000008569 process Effects 0.000 claims abstract description 10
- 238000012163 sequencing technique Methods 0.000 claims description 11
- 230000002452 interceptive effect Effects 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 238000000926 separation method Methods 0.000 claims description 2
- 208000032041 Hearing impaired Diseases 0.000 abstract description 3
- 238000004891 communication Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract 1
- 230000008859 change Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 208000016354 hearing loss disease Diseases 0.000 description 5
- 206010013952 Dysphonia Diseases 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 206010011878 Deafness Diseases 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 238000004873 anchoring Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000009467 reduction 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
- 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
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- 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
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0272—Voice signal separating
-
- 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
- G10L21/06—Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids
- G10L21/10—Transforming into visible information
-
- 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
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L2021/02082—Noise filtering the noise being echo, reverberation of the speech
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Document Processing Apparatus (AREA)
Abstract
A kind of vision hearing aid, it is intended to provide a kind of relative position that can see interlocutor's voice text identified and sound source by hearing impaired persons by speech recognition and synthetic technology, the intention for understanding interlocutor, plays the voice of the reply text of oneself to complete the process with other people speech exchange.It includes sound collection component, language and characters display unit.Sound collection component is a wearable multi-microphone device, for acquiring, extracting the voice messaging of people around and the relative position information of sound source.Language and characters display unit carries out speech recognition to the acoustic information that acquisition comes, and the text importing after identification is come out, while highlighting to the text of the voice of preferred interlocutor.It shows available reply text, then plays the voice of user's selection or the response text of editor, interlocutor is allowed to hear response voice.To the process for helping hearing impaired persons to complete more quickly to carry out speech exchange communication with interlocutor naturally.
Description
Technical field
The sound that hearing aid is captured by processing amplifies after reducing noise, echo cancellation process for user
Sound, so that hearing impaired individual can catch sound.
Background technique
Existing hearing aid can not provide help for the deaf-mute of the absolutely not sense of hearing.
Existing hearing aid is performed poor in the case where having noisy environmental noise or more people while speaking, can not be complete
The noise for shielding ambient enviroment can not also shield the voice of other unrelated personages of surrounding, and user can not be allowed to pass through hearing aid anchor
Determine a main problem existing for the voice and existing hearing aid of interlocutor.
Existing hearing aid does not provide the function of allowing user to issue reply voice by hearing aid, in this case,
Existing hearing aid can be only done the function of unidirectional hearing aid, and can not provide further help dysphonia or have hair
The function that the personage that sound barrier hinders is replied by equipment sounding.
Summary of the invention
The illustrative embodiments conceived according to the present invention, visual vision hearing aid include: sound collection portion
Part is a portable or wearable multi-microphone equipment, by the sound being collected by reducing noise, eliminating back
Sound, the voice signal for identifying people around, separation and Extraction be multichannel independent voice signal, calculate the sound source of each road voice relative to
After the distance of sound collection component and position, by each road voice signal and location information of its sound source relative to sound collection component
Language and characters display unit is given by data link transmission；Language and characters display unit includes governor circuit, loudspeaker, display screen
And processing software；Show to include the first display area, the second display area and third display area on the display interface of screen.It is main
It is text information that circuit and processing software, which are controlled, by the multi-path voice signal identification received；Processing software is by every road voice signal pair
The text information answered is displayed in proportion relative to the relative position of sound collection component and distance in the first viewing area by its sound source
In domain.This makes hearing impairment personage can see the corresponding text of other people sound of periphery, knows other people meaning of speaking
Figure.
The present invention is designed to be badly damaged for the sense of hearing daily life service of personage, sound collection component be once
Take formula or wearable device.In routine use, user can be carried around or dress sound collection component, sound collection portion
The position of part is exactly the body position of carrier or wearer, sound collection component just facing towards being exactly carrier or wearer
Positive direction.
Sound collection component can be used as portable or wearable device and pass through data link to language and characters display unit
Location information of the sound source of voice signal and voice signal relative to sound collection component is sent, accessory is also can be used as and is attached to language
Sound text importing component.
When language and characters display unit only receives voice signal all the way, processing software is using the road voice signal as head
Voice is selected, the text which comes out highlightedly is shown by the time sequencing for receiving the voice signal every time the
Two display areas.
When language and characters display unit, which receives, is more than voice signal all the way, processing software can select sound source away from sound
The carrier of acquisition component or positive nearest, carrier or wearer of the sound source away from sound collection component the front area of wearer
Domain distance recently, the highest voice of intensity of sound as preferred voice, and by the text of the first choice speech recognition out by connecing every time
The time sequencing for receiving the voice signal is successively highlightedly shown in the second display area.
When the carrier of sound collection component or the position of wearer change or the sound source position of the voice of people around,
After intensity of sound changes, the processing software can be reappraised according to the condition of above-mentioned selection first choice voice and be selected most
Qualified voice is as preferred voice, and by the text of the first choice speech recognition out by receiving the voice signal every time
Time sequencing is successively highlightedly shown in the second display area.
User can choose the text information that any one place is shown in the first display area, and processing software can be by user
For the corresponding voice of the text information selected as preferred voice, the text which is identified should by each receive
The time sequencing of voice signal is successively highlightedly shown in the second display area.In the voice signal feelings that can be collected into the voice
Under condition, even if the position of sound collection component itself is changed, or there are other voices to be in and be more preferably selected as first choice
When the condition of voice, processing software keeps the voice for selecting above-mentioned user as preferred voice, until user selects again
Other voices are selected.This allows what user can be convenient to exchange with interlocutor, causes to take in the movement variation of user's body
When the change in location of the sound collection component of band or wearing, when surrounding enviroment have more people while speaking, in interlocutor position itself
It sets when changing, this can allow the voice of user's anchoring and its interlocutor, in dialogue both sides' change in location or other people language
When the variation of sound, keep only showing the text being identified with the voice of its interlocutor in the second display area.
The setting of processing software time according to used in dialogue both sides' maximum single-wheel interactive dialogue process during current session
And dynamic adjusts maximum single-wheel and talks with cycle duration data, if sound collection component is in current maximum single-wheel dialogue cycle duration
Fail to collect the voice signal of current preferred voice, processing software then thinks that current preferred voice thoroughly disappears, can be by
The condition of above-mentioned selection first choice voice reselects new preferred voice, and the text that the preferred speech recognition reselected is gone out
It is highlighted in the second display area of display screen.
Processing software can first empty the second viewing area after reselecting preferred voice or user selected preferred voice
Inherited literal in domain.
Processing software after the newest word content for increasing display, provides one to a plurality of optional in analyzing the second display area
Optimum Matching response word-information display in third display area, given response text information is for interlocutor
The text information of text information and its most common speech response of information above；This text of preferred voice is interior above with it
The text approximation identical or semantic with its content above in dialog procedure, processing software can select before this user Rong Ruoyu before this
The corresponding echo message selected, edit or inputted is placed in the position of override selection；User can directly select respective entries
Response text information, or the response text information of selection edit-modify respective entries or directly inputs response text information, locates
Selection, edit-modify or the response text information directly inputted are synthesized voice and are played by loudspeaker by reason software.It plays
Complete rear governor circuit can issue of short duration slight vibration or light flash and show that speech answering has finished to user.This
A process can allow other people to hear the speech answering of user, and allowing dysphonia or has the personage of dysphonia to could be used that voice
It imparts one's ideas to other people, improves the speed of both sides' exchanges and dialogues, and process is naturally convenient.
Beneficial effect
Conceive according to the present invention, it is surrounding that vision hearing aid can be such that hearing impairment personage sees in the first display area
The text information of the voice of speaker, when someone will engage in the dialogue with it around hearing impairment personage, this can allow the sense of hearing by
The scholar that speaks sarcastically is organic to will appreciate that around someone needs to engage in the dialogue with it to exchange.
Conceive according to the present invention, vision hearing aid can be such that hearing impairment personage sees and voice described in its interlocutor
Text information, this can allow hearing impairment personage and the dialogue process between its interlocutor to become quicker, easy
And it is natural.
Conceive according to the present invention, it, can be automatically by the road when language and characters display unit only receives voice signal all the way
The text importing that voice signal is identified is in the second display area.Under quieter environment, around user only
When one people speaks, this can allow user in the case where not doing any select and set, and immediately appreciate that voice described in interlocutor
Text information and intention.
Conceive according to the present invention, when language and characters display unit is received more than voice signal all the way, processing software meeting
Select carrier away from sound collection component or wearer front recently, the carrier away from sound collection component or wearer just before
Square region distance is nearest, the highest preferred voice of voice conduct of intensity of sound, and persistently go out the preferred speech recognition
Text importing is in the second display area.In the environment of having more people to speak, interlocutor is naturally relative to the position of user
It can make the optimal in above-mentioned selection first choice voice of the voice maximum probability of interlocutor with the intensity of sound naturally of interlocutor
In the condition first selected；This allows user in the environment of having more people while speaking, and is not doing any the case where select andding set
Under, only desired interlocutor can be chosen or reselect immediately by the adjustment of the body position and direction of user.It is this
Selection mode very naturally intuitively, will allow user to be very natural, conveniently, efficiently carry out pair in the environment of more people speak
Words exchange.
Conceive according to the present invention, the corresponding sound source position of text shown in the first display area has been selected in user
Voice as preferred voice after, even if in the case where the position of sound collection component changes or the position of surrounding people
Set or in the case that voice intensity changes, processing software will the voice that selects of user shown as preferred voice.
This allows user when in use, the variation of sound collection component locations will not be caused because of limb action and reselect voice or
Voice can not be selected, this would not influence user and carry out normal limb action during dialogue；It will not be because of dialogue
Person's moving and reselecting preferred voice in session space；In will not speaking up or speak because of the unrelated personage of surrounding
Preferred voice is reselected close to user.This provides a kind of function of being anchored interlocutor and its voice for user, this
For user noisy and competitive voice there are in the environment of provide convenience selection interlocutor means.
Conceive according to the present invention, the text information of preferred voice continuously can be successively highlighted on by processing software
In second display area, this can allow user to see the text information for the voice said before interlocutor at any time, to allow use
More convenient the whole of understanding interlocutor of person is intended to.
Conceive according to the present invention, processing software is according to dialogue both sides' maximum single-wheel interactive dialogue mistake during current session
The Cheng Suoyong time is arranged and dynamic adjusts maximum single-wheel dialogue cycle duration data, when sound collection component is in the maximum single-wheel pair
After talking about the voice signal for failing to collect the preferred voice in waiting time, processing software will reselect preferred voice；This
User can be allowed not have to the voice for after current session person's end-of-dialogue, reselecting other people naturally as preferred voice
Do any other setting or selection movement.
Conceive according to the present invention, every time by the newest word-information display of preferred voice behind the second display area, locates
Reason software can analyze the text information and its information above, show that most common one or more is optional on third display area
Response text, shown response text is the most common response letter for interlocutor's text information and its information above
Breath；If this text of preferred voice and its content above with before text and its content above it is identical or semantic approximate, place
The corresponding return information that user can be selected before this, edited or inputted by reason software is in the position of override selection；This
User can be allowed faster to select or edit echo message, editor is reduced and respond the time that text occupies；User's selection, editor
The response text modified or directly inputted synthesizes voice by governor circuit and is played by loudspeaker；After finishing, voice text
Word display unit can issue of short duration slight vibration or light flash to indicate that voice answering is played and complete.This, which can allow, to send out
Sound or crackjaw personage make a sound during dialogue, reach the similar function of lifting up one's voice.Allowing can not pronounce
Or the inefficient communication means such as crackjaw personage can be no longer dependent on sign language in dialog procedure, text is write, realize people
Voice dialogue between people exchanges.
Detailed description of the invention
Attached drawing 1 is each work of the visual vision hearing aid for the illustrative embodiments conceived according to the present invention
Connection and operating position figure between component.
Appended drawing reference: sound collection component 10, language and characters display unit 20, loudspeaker 21 show screen 22, and first is aobvious
Show region 30, the second display area 31, third display area 32, data link 40.
Specific embodiment
Various illustrative embodiments are described more fully hereinafter with reference to attached drawing, some exemplary implementations are shown
Mode.However, present inventive concept can be embodied there are many different forms, and should not be construed as limited to explain here
The illustrative embodiments stated.
The exemplary embodiments of the present invention idealization illustrative embodiments that the present invention will be described in detail conceives.Therefore,
It can carry out the various change of diagram.Illustrative embodiments are not limited to attached drawing and the shape including component and between component
The variation of connection relationship.
Hereinafter, the illustrative embodiments conceived according to the present invention will describe visual vision hearing aid with reference to Fig. 1
Device.
As shown in Fig. 1, visualization vision hearing aid includes sound collection component 10, is one portable or wearable
Multi-microphone equipment carries out reduction noise to the sound of acquisition, elimination echo, identifies different sound sources, know for acquiring sound
Do not isolate include in collected sound all different peoples each road independent voice signal, calculate the sound of each road voice
Position of the source relative to sound collection component 10, each road voice signal and its sound source that will identify that are relative to sound collection component
10 location information is transferred to language and characters display unit 20 by data link 40.
Language and characters display unit 20 is a portable electronic device comprising loudspeaker 21 shows screen 22 and place
Manage software.It shows on the display interface of screen 22 and includes: the first display area 30, the second display area 31 and third viewing area
Domain 32.
Governor circuit is located at the inside of language and characters display unit, receives sound collection component by data link 40
10 one or more location informations of independent voice signal and its sound source relative to sound collection component 10 sent, processing software
Identify text expressed in every road voice.Processing software is opposite by the sound source of the corresponding voice of text by the text after identification
It is displayed in proportion in the relative position of sound collection component 10 and distance in the corresponding position of the first display area 30.When there is multichannel
It is longer for the text of the every road voice of display as much as possible in the first display area 30 when independent voice is shown simultaneously
Text information will only show a part or scroll, to reduce the screen area of occupancy required for showing every road voice.
When governor circuit only receives voice messaging all the way, processing software is using the voice as preferred voice；Governor circuit
After having received the voice signal every time, processing software identifies the text of the voice signal and receives the voice by governor circuit
The text that successively will identify that of time sequencing be highlightedly shown in the second display area 31.
When governor circuit is received more than voice signal all the way, processing software can select the carrier away from sound collection component
Or wearer front recently, immediately ahead of the carrier away from sound collection component or wearer region distance recently, intensity of sound most
High voice is as preferred voice；After governor circuit receives the first choice voice signal every time, processing software identifies the first choice
The text of voice is simultaneously successively highlightedly shown the text in the second display by the time sequencing that governor circuit receives the voice
In region 31.
When the carrier of sound collection component 10 or the body position of wearer change, the position of interlocutor or sound
Intensity changes, around the position of other talkers or intensity of sound change, and processing software can reselect optimal
First meet the voice of above-mentioned alternative condition as preferred voice, and after having received the first choice voice signal every time, by the first choice
The time sequencing that the text that speech recognition goes out is received the first choice voice by governor circuit every time is successively highlightedly shown in second
In display area 31.
The text of any voice all the way shown in the first display area of user's selection 30, makes the voice become preferred language
Sound；After receiving the first choice voice every time, processing software identifies the text of the first choice voice and by governor circuit governor circuit
The time sequencing for receiving the voice is successively highlightedly shown in the second display area 31.
After user has selected preferred voice, before user reselects other voices as preferred voice, the language
Sound will be always as preferred voice.
After user has selected preferred voice, before the first choice voice thoroughly disappears, which will be always as first choice
Voice.
The setting of processing software time according to used in dialogue both sides' maximum single-wheel interactive dialogue process during current session
Cycle duration data are talked in maximum single-wheel, and dynamic adjusts the data, the maximum single-wheel that sound collection component 10 is arranged in system
After talking with the voice signal for failing to collect preferred voice in cycle duration, then it is assumed that current speech dialog procedure is over,
Processing software can be reselected new preferred voice, and the preferred voice that will be reselected by the condition of above-mentioned selection first choice voice
The text identified is successively highlighted in the second display area of display screen.
When processing software adds the new text of display every time in the second display area 31, the text and its correlation can be searched
The matched response text of most probable above, and the response text information found is shown in third display area 32 by item；
If this text of preferred voice and its content above in dialog procedure before this text and its content above it is identical or semantic
Approximation, the corresponding return information that user can be selected before this, edited or inputted by processing software are in override selection
Position；User can click selection or edit-modify responds content item, can also directly input unrelated with existing response text
New response text；Processing software by the text of the response content of above-mentioned selection, edit-modify or input synthesize voice by
Governor circuit is played by loudspeaker 21；After finishing, governor circuit can issue of short duration slight vibration or of short duration light
Flashing is finished with showing that response text is played.
Claims (6)
1. a kind of vision hearing aid includes sound collection component, language and characters display unit and data link, the voice text
Word display unit includes governor circuit, loudspeaker, display screen and processing software；It is wrapped on the display interface of the display screen
Containing the first display area, the second display area and third display area；It is characterized in that, the sound collection component is one
Portable or wearable multi-microphone equipment, the sound collection component is by identifying people around in collected sound
Voice signal, everyone speech signal separation is extracted as independent voice signal, calculates independent voice signal described in every road
Position of the sound source relative to the sound collection component, independent voice signal described in the every road extracted and its sound source is opposite
The language and characters display unit is given by the data link transmission in the location information of the sound collection component；It is described
Governor circuit receive the location information of voice signal described in every road and its sound source relative to the sound collection component, the place
Reason software identifies the text information of voice signal described in every road, will identify that the text information come is opposite by its sound source
It is displayed in proportion on first display area in the position of the sound collection component and distance；The processing software by
The text that wherein voice signal is identified all the way is selected highlightedly to be shown in described second in the voice signal aobvious
Show in region；The processing software according in the second display area newest text and its associated text above content provide one or more
The response content of the optional editable Optimum Matching of item is shown in the third display area, user's selection, editor or straight
After connecing input response content, response content is synthesized voice and is played by the loudspeaker by the processing software.
2. a kind of vision hearing aid according to claim 1, which is characterized in that the language and characters display unit is only
When receiving voice signal all the way and its location information, the processing software using the voice signal as preferred voice,
The text that the preferred voice is identified is received the first choice by the governor circuit by the processing software every time
Successively highlightedly addition is shown in second display area to the time sequencing of voice signal.
3. a kind of vision hearing aid according to claim 1, which is characterized in that the language and characters display unit is connecing
In the case where receiving more than voice signal all the way and its location information, the processing software chooses the sound source position of the voice
Sound source position positioned at the carrier of the sound collection component or the front of wearer apart from nearest, the described voice is away from described
Sound collection component carrier or nearest, the described voice of region distance immediately ahead of wearer the highest voice of intensity of sound
As preferred voice, the text that the preferred voice is identified by the processing software is each by the governor circuit
The time sequencing for receiving the preferred voice signal is highlightedly shown in second display area.
4. a kind of vision hearing aid according to claim 1, which is characterized in that in user's selection first display
After any one text information shown in region, the processing software chooses the corresponding language of text of user's selection
For sound as preferred voice, the text that the processing software goes out the preferred speech recognition is each by the governor circuit
The time sequencing for receiving the preferred voice signal is successively highlighted on second display area；Further, institute
Stating processing software can be always using the voice as preferred voice until user has reselected other voices as newly
Preferred voice.
5. a kind of vision hearing aid described in -4 according to claim 1, which is characterized in that the processing software is according to current session
The maximum single-wheel dialogue cycle duration data of the setting of time used in dialogue both sides' maximum single-wheel interactive dialogue process in the process, and with
Dialog procedure dynamic adjusts the maximum single-wheel dialogue cycle duration data, and the sound collection component is single in the maximum
After wheel talks with the voice signal for failing to collect the preferred voice in cycle duration, the processing software will reselect head
Select voice.
6. a kind of vision hearing aid described in -5 according to claim 1, which is characterized in that the processing software is according to described
The content of every newest word content in second display area and its associated text above provides and shows one to a plurality of optimal
The response content matched, in selection or edit-modify or after directly inputting response content, the processing software can incite somebody to action user
The text for the response content that the user finally determines synthesizes voice and is played by the loudspeaker；The master control
Described in circuit carries out of short duration slight vibration after playing the voice of text of the responses content or light flash shows
The voice for responding the text of content has finished.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811567610.4A CN109616122A (en) | 2018-12-25 | 2018-12-25 | A kind of visualization hearing aid |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811567610.4A CN109616122A (en) | 2018-12-25 | 2018-12-25 | A kind of visualization hearing aid |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109616122A true CN109616122A (en) | 2019-04-12 |
Family
ID=66009866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811567610.4A Pending CN109616122A (en) | 2018-12-25 | 2018-12-25 | A kind of visualization hearing aid |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109616122A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111358066A (en) * | 2020-03-10 | 2020-07-03 | 中国人民解放军陆军军医大学第一附属医院 | Protective clothing based on speech recognition |
| CN113825079A (en) * | 2021-09-11 | 2021-12-21 | 武汉左点科技有限公司 | Method and device for enhancing sound wave acceptance of hearing aid |
| CN114143591A (en) * | 2021-11-26 | 2022-03-04 | 网易（杭州）网络有限公司 | Subtitle display method, device, terminal and machine-readable storage medium |
| CN114615609A (en) * | 2022-03-15 | 2022-06-10 | 深圳市昂思科技有限公司 | Hearing aid control method, hearing aid device, apparatus, device and computer medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003223199A (en) * | 2002-01-28 | 2003-08-08 | Telecommunication Advancement Organization Of Japan | Preparation support system for writing-up text for superimposed character and semiautomatic superimposed character program production system |
| CN201860365U (en) * | 2010-05-26 | 2011-06-08 | 康佳集团股份有限公司 | Mobile phone device for deaf-mute |
| CN104503572A (en) * | 2014-12-16 | 2015-04-08 | 芜湖乐锐思信息咨询有限公司 | Voice-text interaction and conversion device |
| CN105007557A (en) * | 2014-04-16 | 2015-10-28 | 上海柏润工贸有限公司 | Intelligent hearing aid with voice identification and subtitle display functions |
| CN105103457A (en) * | 2013-03-28 | 2015-11-25 | 三星电子株式会社 | Portable terminal, hearing aid, and method of indicating positions of sound sources in the portable terminal |
| CN105554662A (en) * | 2015-06-30 | 2016-05-04 | 宇龙计算机通信科技(深圳)有限公司 | Hearing-aid glasses and hearing-aid method |
| CN106686223A (en) * | 2016-12-19 | 2017-05-17 | 中国科学院计算技术研究所 | A system and method for assisting dialogues between a deaf person and a normal person, and a smart mobile phone |
| CN108962254A (en) * | 2018-06-11 | 2018-12-07 | 北京佳珥医学科技有限公司 | For assisting the methods, devices and systems and augmented reality glasses of hearing-impaired people |
| CN109032545A (en) * | 2018-06-11 | 2018-12-18 | 北京佳珥医学科技有限公司 | For providing the method and apparatus and augmented reality glasses of sound source information |
-
2018
- 2018-12-25 CN CN201811567610.4A patent/CN109616122A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003223199A (en) * | 2002-01-28 | 2003-08-08 | Telecommunication Advancement Organization Of Japan | Preparation support system for writing-up text for superimposed character and semiautomatic superimposed character program production system |
| CN201860365U (en) * | 2010-05-26 | 2011-06-08 | 康佳集团股份有限公司 | Mobile phone device for deaf-mute |
| CN105103457A (en) * | 2013-03-28 | 2015-11-25 | 三星电子株式会社 | Portable terminal, hearing aid, and method of indicating positions of sound sources in the portable terminal |
| CN105007557A (en) * | 2014-04-16 | 2015-10-28 | 上海柏润工贸有限公司 | Intelligent hearing aid with voice identification and subtitle display functions |
| CN104503572A (en) * | 2014-12-16 | 2015-04-08 | 芜湖乐锐思信息咨询有限公司 | Voice-text interaction and conversion device |
| CN105554662A (en) * | 2015-06-30 | 2016-05-04 | 宇龙计算机通信科技(深圳)有限公司 | Hearing-aid glasses and hearing-aid method |
| CN106686223A (en) * | 2016-12-19 | 2017-05-17 | 中国科学院计算技术研究所 | A system and method for assisting dialogues between a deaf person and a normal person, and a smart mobile phone |
| CN108962254A (en) * | 2018-06-11 | 2018-12-07 | 北京佳珥医学科技有限公司 | For assisting the methods, devices and systems and augmented reality glasses of hearing-impaired people |
| CN109032545A (en) * | 2018-06-11 | 2018-12-18 | 北京佳珥医学科技有限公司 | For providing the method and apparatus and augmented reality glasses of sound source information |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111358066A (en) * | 2020-03-10 | 2020-07-03 | 中国人民解放军陆军军医大学第一附属医院 | Protective clothing based on speech recognition |
| CN113825079A (en) * | 2021-09-11 | 2021-12-21 | 武汉左点科技有限公司 | Method and device for enhancing sound wave acceptance of hearing aid |
| CN114143591A (en) * | 2021-11-26 | 2022-03-04 | 网易（杭州）网络有限公司 | Subtitle display method, device, terminal and machine-readable storage medium |
| CN114615609A (en) * | 2022-03-15 | 2022-06-10 | 深圳市昂思科技有限公司 | Hearing aid control method, hearing aid device, apparatus, device and computer medium |
| CN114615609B (en) * | 2022-03-15 | 2024-01-30 | 深圳市昂思科技有限公司 | Hearing aid control method, hearing aid device, apparatus, device and computer medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109616122A (en) | A kind of visualization hearing aid | |
| US20220159403A1 (en) | System and method for assisting selective hearing | |
| US9769296B2 (en) | Techniques for voice controlling bluetooth headset | |
| US9949056B2 (en) | Method and apparatus for presenting to a user of a wearable apparatus additional information related to an audio scene | |
| US6882971B2 (en) | Method and apparatus for improving listener differentiation of talkers during a conference call | |
| CN108156550B (en) | Playing method and device of headset | |
| CN108762494B (en) | Method, device and storage medium for displaying information | |
| US20170243582A1 (en) | Hearing assistance with automated speech transcription | |
| WO2021136962A1 (en) | Hearing aid systems and methods | |
| JP2016051081A (en) | Device and method of sound source separation | |
| US20180054688A1 (en) | Personal Audio Lifestyle Analytics and Behavior Modification Feedback | |
| US20230164509A1 (en) | System and method for headphone equalization and room adjustment for binaural playback in augmented reality | |
| CN111741394A (en) | Data processing method and device and readable medium | |
| JP2020095121A (en) | Speech recognition system, generation method for learned model, control method for speech recognition system, program, and moving body | |
| CN104851423B (en) | Sound information processing method and device | |
| US20240135951A1 (en) | Mapping sound sources in a user interface | |
| CN107767862B (en) | Voice data processing method, system and storage medium | |
| CN110176231B (en) | Sound output system, sound output method, and storage medium | |
| KR20140093459A (en) | Method for automatic speech translation | |
| EP3288035B1 (en) | Personal audio analytics and behavior modification feedback | |
| CN112673423A (en) | In-vehicle voice interaction method and equipment | |
| CN111988705A (en) | Audio processing method, device, terminal and storage medium | |
| CN113066513B (en) | Voice data processing method and device, electronic equipment and storage medium | |
| US20220172711A1 (en) | System with speaker representation, electronic device and related methods | |
| CN112331179A (en) | Data processing method and earphone accommodating device |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190412 |