CN110516265A - A kind of single identification real-time translation system based on intelligent sound - Google Patents
A kind of single identification real-time translation system based on intelligent sound Download PDFInfo
- Publication number
- CN110516265A CN110516265A CN201910819189.XA CN201910819189A CN110516265A CN 110516265 A CN110516265 A CN 110516265A CN 201910819189 A CN201910819189 A CN 201910819189A CN 110516265 A CN110516265 A CN 110516265A
- Authority
- CN
- China
- Prior art keywords
- sound
- user
- module
- voice signal
- system based
- 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
- 238000013519 translation Methods 0.000 title claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 28
- 230000001755 vocal effect Effects 0.000 claims abstract description 11
- 230000000694 effects Effects 0.000 claims abstract description 5
- 230000005236 sound signal Effects 0.000 claims abstract description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000003786 synthesis reaction Methods 0.000 claims description 6
- 206010011224 Cough Diseases 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000009432 framing Methods 0.000 claims description 3
- 230000010355 oscillation Effects 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 206010041232 sneezing Diseases 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims 1
- 235000016838 Pomo dAdamo Nutrition 0.000 description 3
- 244000003138 Pomo dAdamo Species 0.000 description 3
- 230000007306 turnover Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/005—Language recognition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/06—Decision making techniques; Pattern matching strategies
- G10L17/14—Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/22—Interactive procedures; Man-machine interfaces
Abstract
The invention discloses a kind of single identification real-time translation system based on intelligent sound, it is related to the communications field, including sound acquisition module, sound processing module, achieve writing module and putting module, sound acquisition module collected sound signal simultaneously transmits, sound processing module receives and processing voice signal, user's throat is experienced according to vibration sensor whether vibrate establish user's sound bank and contrast phone library, feature identification is carried out to user's vocal print, obtain user's voice signal, it is compared with contrast phone library, further reject the voice of environment noise and other people, obtain the text information of language described in user, writing module is achieved by character translation into object language, and switch to the manuscript storage of minutes mode, manuscript is shown or is played by putting module.The present invention accurately identifies the sound of speaking of single use person, ignores other people one's voices in speech, then environment noise is filtered, single identification, real time translation, and translation is more accurate, and effect is more preferable.
Description
Technical field
The present invention relates to the communications field, especially a kind of single identification real-time translation system based on intelligent sound.
Background technique
With the development of science and technology the increasingly many and diverse and information content of international exchange sharply increases, the obstacle between different language
Caused Information Problems increasingly influence the efficiency linked up, and human translation is needed to turn over the speech of participant in real time
It translates, not only human cost is high, but also often occurs during human translation because interrupting caused by thinking.In the prior art
Real time translation is carried out to the speech in meeting using machine translation mode, but due to sound source complex, noise in meeting room
It is more, it is directly acquired using microphone, whether be user one's voice in speech, therefore collected sound presss from both sides if can not accurately identify
Miscellaneous a large amount of independent voices cause sound identification and translation mistake occur, are unfavorable for real time translation, and the sound without the noise reduction process that cleans
The directly processing of message breath is easier to cause to identify mistake.
Summary of the invention
In order to overcome the drawbacks described above in the presence of the prior art, the present invention provides a kind of based on the single of intelligent sound
Identify real-time translation system.The technical solution adopted by the present invention to solve the technical problems is: a kind of list based on intelligent sound
One identification real-time translation system, including sound acquisition module, sound processing module, archive writing module and putting module:
S1. the sound acquisition module collected sound signal and sound processing module is sent by voice signal；
S2. the sound processing module receives the voice signal of sound acquisition module, identifies the sound and language of user
Type establishes user's sound bank and contrast phone library, rejects the sound of noise and other people, the voice signal translated to needs
It is handled, obtain the corresponding text of language described in user and sends archive writing module for text information；
S3. the archive writing module by character translation at object language, and switch to minutes mode manuscript storage；
S4. manuscript is launched out or be broadcast using speech synthesis player by the putting module by display
It puts.
A kind of above-mentioned single identification real-time translation system based on intelligent sound, the sound acquisition module are miniature ear
Wheat, earphone, microphone and the external vibration sensor for touching throat including being inserted into human ear.
A kind of above-mentioned single identification real-time translation system based on intelligent sound, the sound processing module of stating is with sound
Line recognition unit carries out feature identification to user's vocal print.
A kind of above-mentioned single identification real-time translation system based on intelligent sound, the miniature headset pass through bluetooth or net
Network is connect with control device, and the control device is controlled by computer and connected.
A kind of above-mentioned single identification real-time translation system based on intelligent sound, the noise include cough, sneezing,
Sound of the wind browses sound.
A kind of above-mentioned single identification real-time translation system based on intelligent sound, the working-flow are as follows:
A. the preparation stage, user is in quieter environment and wears miniature headset and carry out trying to speak, described miniature
The external vibration sensor for touching throat of headset experiences vibration and records oscillation intensity, and the miniature headset will be adopted
The voice signal of collection passes to sound recognition module, the sound and category of language of the sound recognition module identification user, sound
Line recognition unit carries out feature identification to user's vocal print and establishes user's sound bank；
B. formally in use, vibration sensor cannot experience throat when user speaks when wearer is silent
Vibration, miniature headset acquires the hum in ambient enviroment and the voice in addition to user and in sound recognition module at this time
Contrast phone library is established under effect；
C. when wearer loquiturs, the external vibration sensor of the miniature headset experiences throat when user speaks
The vibration of generated sufficient intensity, and trigger the judgement for the sound bank that sound processing module should be stored in voice signal, sound
The voice signal that sound acquisition module is sent therefrom extracted by sound processing module meet user's vocal print feature audio deposit make
User's sound bank, and user's sound bank and contrast phone library are compared, filtering noise is further rejected, obtains and needs to turn over
The voice signal translated；
D. sound processing module carries out framing and feature extraction to the voice signal that needs are translated, with linear prediction cepstrum coefficient
Every frame sound is become the multi-C vector comprising acoustic information by coefficient, is obtained audio data, is passed through acoustic model, dictionary and language
Model carries out text output to the audio data after feature extraction, obtains the corresponding text of language described in user and believes text
Breath is sent to archive writing module；
E. it is regular to text progress to achieve writing module, the sentence for meeting specification is organized into, by the character cell of input, sequence
Column upload cloud, and object language needed for translating into user is switched to the manuscript of minutes mode and storage；
F. putting module is as needed, and manuscript is launched out by display, or using speech synthesis player into
Row plays.
The invention has the advantages that the present invention, which passes through, judges that the vibration of Adam's apple triggers sound processing module and sound is believed
The judgement of number processing mode, voice signal collected is stored in contrast phone library as a comparison when being not felt by Adam's apple vibration, feels
Voice signal collected when being vibrated by Adam's apple, the voice of user is therefrom extracted by Application on Voiceprint Recognition unit, is established and is used
Person's sound bank, the sound of the single speaker of identification that can be more accurate, user's sound bank and contrast phone library are carried out
Comparison, preferably ignores other people one's voices in speech, can filter environment noise thoroughly, single identification, real time translation, translation is more
Accurately, effect is more preferable.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is schematic diagram of the invention；
Fig. 2 is the schematic diagram of sound collection of the present invention.
Specific embodiment
In order to illustrate more clearly of technical solution of the present invention, following further describes the present invention with reference to the drawings,
It should be evident that drawings described below is only one embodiment of the present of invention, for those of ordinary skill in the art
For, without creative efforts, other embodiments are obtained according to this drawings and examples, belong to this hair
Bright protection scope.
A kind of single identification real-time translation system based on intelligent sound, including sound acquisition module, sound processing module,
Achieve writing module and putting module:
S1. the sound acquisition module collected sound signal and sound processing module is sent by voice signal；
S2. the sound processing module receives the voice signal of sound acquisition module, identifies the sound and language of user
Type establishes user's sound bank and contrast phone library, rejects the sound of noise and other people, the voice signal translated to needs
It is handled, obtain the corresponding text of language described in user and sends archive writing module for text information；
S3. the archive writing module by character translation at object language, and switch to minutes mode manuscript storage；
S4. manuscript is launched out or be broadcast using speech synthesis player by the putting module by display
It puts.
Detailed, the sound acquisition module is miniature headset, earphone, microphone and external touching including being inserted into human ear
And the vibration sensor of throat, the sound processing module carry out feature knowledge to user's vocal print with Application on Voiceprint Recognition unit
Not, the miniature headset is connect by bluetooth or network with control device, and the control device is controlled by computer and connected, described
Noise includes cough, sneezing, sound of the wind, browses sound, the working-flow are as follows:
A. the preparation stage, user is in quieter environment and wears miniature headset and carry out trying to speak, described miniature
The external vibration sensor for touching throat of headset experiences vibration and records oscillation intensity, and the miniature headset will be adopted
The voice signal of collection passes to sound recognition module, the sound and category of language of the sound recognition module identification user, sound
Line recognition unit carries out feature identification to user's vocal print and establishes user's sound bank；
B. formally in use, vibration sensor cannot experience throat when user speaks when wearer is silent
Vibration, miniature headset acquires the hum in ambient enviroment and the voice in addition to user and in sound recognition module at this time
Contrast phone library is established under effect；
C. when wearer loquiturs, the external vibration sensor of the miniature headset experiences throat when user speaks
The vibration of generated sufficient intensity, and trigger the judgement for the sound bank that sound processing module should be stored in voice signal, sound
The voice signal that sound acquisition module is sent therefrom extracted by sound processing module meet user's vocal print feature audio deposit make
User's sound bank, and user's sound bank and contrast phone library are compared, filtering noise is further rejected, obtains and needs to turn over
The voice signal translated；
D. sound processing module carries out framing and feature extraction to the voice signal that needs are translated, with linear prediction cepstrum coefficient
Every frame sound is become the multi-C vector comprising acoustic information by coefficient, is obtained audio data, is passed through acoustic model, dictionary and language
Model carries out text output to the audio data after feature extraction, obtains the corresponding text of language described in user and believes text
Breath is sent to archive writing module；
E. it is regular to text progress to achieve writing module, the sentence for meeting specification is organized into, by the character cell of input, sequence
Column upload cloud, and object language needed for translating into user is switched to the manuscript of minutes mode and storage；
F. putting module is as needed, and manuscript is launched out by display, is broadcast using speech synthesis player
It puts.
Above embodiments are only exemplary embodiment of the present invention, are not used in the limitation present invention, protection scope of the present invention
It is defined by the claims.Those skilled in the art can within the spirit and scope of the present invention make respectively the present invention
Kind modification or equivalent replacement, this modification or equivalent replacement also should be regarded as being within the scope of the present invention.
Claims (6)
1. a kind of single identification real-time translation system based on intelligent sound, including sound acquisition module, sound processing module, deposit
Shelves writing module and putting module, it is characterised in that:
S1. the sound acquisition module collected sound signal and sound processing module is sent by voice signal；
S2. the sound processing module receives the voice signal of sound acquisition module, identifies the sound and category of language of user,
User's sound bank and contrast phone library are established, the sound of noise and other people is rejected, the voice signal that needs are translated is carried out
Processing obtains the corresponding text of language described in user and sends archive writing module for text information；
S3. the archive writing module will acquire character translation into object language, and switch to the manuscript storage of minutes mode；
S4. manuscript is launched out or be played out using speech synthesis player by the putting module by display.
2. a kind of single identification real-time translation system based on intelligent sound according to claim 1, which is characterized in that institute
Stating sound acquisition module is miniature headset, earphone, microphone and the external vibrating sensing for touching throat including being inserted into human ear
Device.
3. a kind of single identification real-time translation system based on intelligent sound according to claim 1, which is characterized in that institute
It states sound processing module and feature identification is carried out to user's vocal print with Application on Voiceprint Recognition unit.
4. a kind of single identification real-time translation system based on intelligent sound according to claim 2, which is characterized in that institute
It states miniature headset to connect by bluetooth or network with control device, the control device is controlled by computer and connected.
5. a kind of single identification real-time translation system based on intelligent sound according to claim 1, which is characterized in that institute
Noise is stated to include cough, sneezing, sound of the wind, browse sound.
6. a kind of single identification real-time translation system based on intelligent sound according to claim 1, which is characterized in that institute
State working-flow are as follows:
A. preparation stage, user are in quieter environment and wear miniature headset and carry out trying to speak, the miniature headset
The external vibration sensor for touching throat experiences throat and vibrates and record oscillation intensity, and the miniature headset is by acquisition
Voice signal passes to sound recognition module, the sound and category of language of the sound recognition module identification user, and vocal print is known
Other unit carries out feature identification to user's vocal print and establishes user's sound bank；
B. formal in use, vibration sensor cannot experience the vibration of throat when user speaks when wearer is silent,
Hum in miniature headset acquisition ambient enviroment and the voice in addition to user and the effect in sound recognition module at this time
Under establish contrast phone library；
C. when wearer loquiturs, the external vibration sensor of the miniature headset is experienced throat when user speaks and is produced
The vibration of raw sufficient intensity, and the judgement for the sound bank that sound processing module should be stored in voice signal is triggered, sound is adopted
The voice signal that collection module is sent therefrom is extracted the audio deposit user for meeting user's vocal print feature by sound processing module
Sound bank, and user's sound bank and contrast phone library are compared, filtering noise is further rejected, obtains what needs were translated
Voice signal；
D. sound processing module carries out framing and feature extraction to the voice signal that needs are translated, with linear prediction residue error
Every frame sound is become into the multi-C vector comprising acoustic information, audio data is obtained, passes through acoustic model, dictionary and language model
Text output is carried out to the audio data after feature extraction, obtain the corresponding text of language described in user and sends out text information
It is sent to archive writing module；
E. it is regular to text progress to achieve writing module, is organized into the sentence for meeting specification, it will be in the character cell of input, sequence
Cloud is passed, object language needed for translating into user is switched to the manuscript of minutes mode and storage；
F. putting module is as needed, manuscript is launched out by display, or broadcast using speech synthesis player
It puts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910819189.XA CN110516265A (en) | 2019-08-31 | 2019-08-31 | A kind of single identification real-time translation system based on intelligent sound |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910819189.XA CN110516265A (en) | 2019-08-31 | 2019-08-31 | A kind of single identification real-time translation system based on intelligent sound |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110516265A true CN110516265A (en) | 2019-11-29 |
Family
ID=68629934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910819189.XA Pending CN110516265A (en) | 2019-08-31 | 2019-08-31 | A kind of single identification real-time translation system based on intelligent sound |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110516265A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111601208A (en) * | 2020-06-24 | 2020-08-28 | 佛山科学技术学院 | Noise reduction translation earphone and translation method thereof |
| CN112967723A (en) * | 2021-02-01 | 2021-06-15 | 珠海格力电器股份有限公司 | Identity confirmation method and control device, and sleep parameter detection method and control device |
| WO2021134284A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳市欢太科技有限公司 | Voice information processing method, hub device, control terminal and storage medium |
| CN113413613A (en) * | 2021-06-17 | 2021-09-21 | 网易（杭州）网络有限公司 | Method and device for optimizing voice chat in game, electronic equipment and medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002204489A (en) * | 2000-12-28 | 2002-07-19 | Nec Saitama Ltd | Earphone microphone |
| CN201532762U (en) * | 2009-06-04 | 2010-07-21 | 成都信息工程学院 | Simultaneous interpretation device special for individuals |
| CN101950564A (en) * | 2010-10-13 | 2011-01-19 | 镇江华扬信息科技有限公司 | Remote digital voice acquisition, analysis and identification system |
| CN106454605A (en) * | 2016-11-30 | 2017-02-22 | 南京小脚印网络科技有限公司 | Intelligent translation earphone system |
| CN106486125A (en) * | 2016-09-29 | 2017-03-08 | 安徽声讯信息技术有限公司 | A kind of simultaneous interpretation system based on speech recognition technology |
| CN108010524A (en) * | 2017-12-04 | 2018-05-08 | 深圳市沃特沃德股份有限公司 | Speech translation system and method |
| CN108447497A (en) * | 2018-03-07 | 2018-08-24 | 陈勇 | A method of independently going out oneself sounding in noisy environment |
| CN109033092A (en) * | 2018-06-13 | 2018-12-18 | 深圳市思创达塑胶模具有限公司 | A kind of real-time translation system, method and interpreting equipment |
| CN109376363A (en) * | 2018-09-04 | 2019-02-22 | 出门问问信息科技有限公司 | A kind of real-time voice interpretation method and device based on earphone |
| CN109545216A (en) * | 2018-12-28 | 2019-03-29 | 合肥凯捷技术有限公司 | A kind of audio recognition method and speech recognition system |
| CN109686363A (en) * | 2019-02-26 | 2019-04-26 | 深圳市合言信息科技有限公司 | A kind of on-the-spot meeting artificial intelligence simultaneous interpretation equipment |
| CN109977427A (en) * | 2019-03-12 | 2019-07-05 | 东华大学 | A kind of miniature wearable real time translator |
-
2019
- 2019-08-31 CN CN201910819189.XA patent/CN110516265A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002204489A (en) * | 2000-12-28 | 2002-07-19 | Nec Saitama Ltd | Earphone microphone |
| CN201532762U (en) * | 2009-06-04 | 2010-07-21 | 成都信息工程学院 | Simultaneous interpretation device special for individuals |
| CN101950564A (en) * | 2010-10-13 | 2011-01-19 | 镇江华扬信息科技有限公司 | Remote digital voice acquisition, analysis and identification system |
| CN106486125A (en) * | 2016-09-29 | 2017-03-08 | 安徽声讯信息技术有限公司 | A kind of simultaneous interpretation system based on speech recognition technology |
| CN106454605A (en) * | 2016-11-30 | 2017-02-22 | 南京小脚印网络科技有限公司 | Intelligent translation earphone system |
| CN108010524A (en) * | 2017-12-04 | 2018-05-08 | 深圳市沃特沃德股份有限公司 | Speech translation system and method |
| CN108447497A (en) * | 2018-03-07 | 2018-08-24 | 陈勇 | A method of independently going out oneself sounding in noisy environment |
| CN109033092A (en) * | 2018-06-13 | 2018-12-18 | 深圳市思创达塑胶模具有限公司 | A kind of real-time translation system, method and interpreting equipment |
| CN109376363A (en) * | 2018-09-04 | 2019-02-22 | 出门问问信息科技有限公司 | A kind of real-time voice interpretation method and device based on earphone |
| CN109545216A (en) * | 2018-12-28 | 2019-03-29 | 合肥凯捷技术有限公司 | A kind of audio recognition method and speech recognition system |
| CN109686363A (en) * | 2019-02-26 | 2019-04-26 | 深圳市合言信息科技有限公司 | A kind of on-the-spot meeting artificial intelligence simultaneous interpretation equipment |
| CN109977427A (en) * | 2019-03-12 | 2019-07-05 | 东华大学 | A kind of miniature wearable real time translator |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021134284A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳市欢太科技有限公司 | Voice information processing method, hub device, control terminal and storage medium |
| CN111601208A (en) * | 2020-06-24 | 2020-08-28 | 佛山科学技术学院 | Noise reduction translation earphone and translation method thereof |
| CN112967723A (en) * | 2021-02-01 | 2021-06-15 | 珠海格力电器股份有限公司 | Identity confirmation method and control device, and sleep parameter detection method and control device |
| CN113413613A (en) * | 2021-06-17 | 2021-09-21 | 网易（杭州）网络有限公司 | Method and device for optimizing voice chat in game, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110516265A (en) | A kind of single identification real-time translation system based on intelligent sound | |
| CN108159702B (en) | Multi-player voice game processing method and device | |
| US20130211826A1 (en) | Audio Signals as Buffered Streams of Audio Signals and Metadata | |
| KR101108114B1 (en) | System and method for analyzing continuous sound, expressing emotion and producing communication about pet dog | |
| CN109074806A (en) | Distributed audio output is controlled to realize voice output | |
| CN105206271A (en) | Intelligent equipment voice wake-up method and system for realizing method | |
| CA2311439A1 (en) | Conversational data mining | |
| CN107112026A (en) | System, the method and apparatus for recognizing and handling for intelligent sound | |
| CN107210040A (en) | The operating method of phonetic function and the electronic equipment for supporting this method | |
| CN100592749C (en) | Conversation assisting system and method | |
| CN108198569A (en) | A kind of audio-frequency processing method, device, equipment and readable storage medium storing program for executing | |
| CN110097890A (en) | A kind of method of speech processing, device and the device for speech processes | |
| US11862153B1 (en) | System for recognizing and responding to environmental noises | |
| US20210343270A1 (en) | Speech translation method and translation apparatus | |
| CN107093421A (en) | A kind of speech simulation method and apparatus | |
| CN107277276A (en) | One kind possesses voice control function smart mobile phone | |
| CN110223711A (en) | Interactive voice based on microphone signal wakes up electronic equipment, method and medium | |
| CN110111776A (en) | Interactive voice based on microphone signal wakes up electronic equipment, method and medium | |
| JP2009178783A (en) | Communication robot and its control method | |
| CN116420188A (en) | Speech filtering of other speakers from call and audio messages | |
| CN110232909A (en) | A kind of audio-frequency processing method, device, equipment and readable storage medium storing program for executing | |
| TW201826167A (en) | Method for face expression feedback and intelligent robot | |
| JP7400364B2 (en) | Speech recognition system and information processing method | |
| CN107322593A (en) | Can outdoor moving company family endowment robot | |
| TW200413961A (en) | Device using handheld communication equipment to calculate and process natural language and method thereof |
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: 20191129 |