CN108364663A - A kind of method and module of automatic recording voice - Google Patents
A kind of method and module of automatic recording voice Download PDFInfo
- Publication number
- CN108364663A CN108364663A CN201810001321.1A CN201810001321A CN108364663A CN 108364663 A CN108364663 A CN 108364663A CN 201810001321 A CN201810001321 A CN 201810001321A CN 108364663 A CN108364663 A CN 108364663A
- Authority
- CN
- China
- Prior art keywords
- sound
- voice
- recording
- prerecording
- current
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
- G10L25/84—Detection of presence or absence of voice signals for discriminating voice from noise
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B20/00—Signal processing not specific to the method of recording or reproducing; Circuits therefor
- G11B20/10—Digital recording or reproducing
- G11B20/10527—Audio or video recording; Data buffering arrangements
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B20/00—Signal processing not specific to the method of recording or reproducing; Circuits therefor
- G11B20/10—Digital recording or reproducing
- G11B20/10527—Audio or video recording; Data buffering arrangements
- G11B2020/10537—Audio or video recording
- G11B2020/10546—Audio or video recording specifically adapted for audio data
Abstract
The invention discloses a kind of method and module of automatic recording voice, belong to voice recognition and recording field, technical problems to be solved are how accurate automatic identification and to record voice.Its method is and the automatic recording voice by intensity of sound and sound frequency automatic identification voice, including：Identify voice：The current sound listened to and preset intensity of sound and sound frequency are compared, if current sound meets preset intensity of sound and sound frequency, judge current sound for voice；Record voice：After listening to voice, sound recording is automatically turned on, carries out voice recording；Preserve voice：Current sound in the predetermined amount of time listened to is compared with preset intensity of sound and sound frequency, if current sound does not meet preset intensity of sound or sound frequency, judges that current voice terminates, ends automatically sound recording and preserve the voice of recording.And structure includes sound monitoring unit and sound recording elements.
Description
Technical field
The present invention relates to voice recognition and the field of recording, the specifically a kind of methods and module of automatic recording voice.
Background technology
Intelligent sound consulting is the critical function of self-aided terminal, and speech recognition is its core technology, and voice collecting is as language
A part for sound identification is very crucial part, it is achieved that client carries out automatic identification and acquisition sound when business consultation
Sound can advanced optimize the function of self-aided terminal, preferably be experienced to user.
The scheme for the voice collecting that intelligent sound consulting system used originally is that user is allowed to click " speech recognition " work(manually
It can directly start to record afterwards, recording terminates to record and preserve after continuing for some time.This indiscriminate live pick-up mode
User experience is not so good, if user in short says it is too short, record can preserve one section of very long invalid fragments；If
User in short says it is too long, then record will lose a part of effective segment.
Above-mentioned voice collecting mechanism can not adapt to changeable playback environ-ment, can not accomplish top quality user experience.For
This passive voice of change records mode, and the method for introducing automatic recording voice, this method can monitor voice
It generates and disappears, realize the automatic recording of voice, user is made to have better self-service experience.
How accurate automatic identification and voice is recorded, is the technical issues that need to address.
Invention content
The technical assignment of the present invention is to be directed to the above shortcoming, provides a kind of method and module of automatic recording voice,
To solve the problems, such as how accurate automatic identification and to record voice.
The technical solution adopted by the present invention to solve the technical problems is：
A kind of method of automatic recording voice, by intensity of sound and sound frequency automatic identification voice, and automatic recording voice,
Including：
Identify voice：The current sound listened to and preset intensity of sound and sound frequency are compared, if current sound
Meet preset intensity of sound and sound frequency, then judges current sound for voice；
Record voice：After listening to voice, sound recording is automatically turned on, carries out voice recording；
Preserve voice：Current sound in the predetermined amount of time listened to is opposed with preset intensity of sound and sound frequency
Than if current sound does not meet preset intensity of sound or sound frequency, judging that current voice terminates, ending automatically sound
The voice that Record and Save is recorded.
Preset sound intensity and sound frequency are basis for estimation, and judgement identification is carried out to the sound listened to, when recognizing
After voice, automatically turns on voice and record, when the sound listened within a predetermined period of time does not meet preset intensity of sound or sound
After voice frequency, it is believed that this section of voice terminates, then terminates the current voice of Record and Save recording, to realize the automatic of voice
Identification, automatic recording and end are recorded, and avoid the unlatching and reception that manually carry out voice recording, and pass through intensity of sound harmony
The setting of voice frequency can exclusive segment noise.
Further, identification voice includes the following steps：
Audio intensity threshold is set as unit of decibel, and sets sound frequency waving interval；
The current sound listened to and intensity of sound standard value are compared, if the intensity of sound of current sound is strong more than sound
Threshold value is spent, then carries out sound frequency judgement；
Current sound frequency and sound frequency waving interval are compared, if the sound frequency of current sound is in sound audio
Rate waving interval then judges current sound for voice.
It passes sequentially through intensity of sound and sound frequency screens sound, can accurately filter out voice, realize certainly
The accuracy of dynamic identification voice.
Further, sound frequency waving interval is set as 300Hz-3400Hz.
Further, before recording voice, cycle carries out prescoring while identifying voice, and prescoring includes：It is supervising
A sound prerecording is carried out while listening at predetermined time intervals, in cyclic process it is unidentified to voice when, empty one
The sound of a prerecording simultaneously carries out sound prerecording next time, when recognizing voice in cyclic process, retains the sound of prerecording
And enters and record voice step.
It is then turned on sound recording after recognizing voice, there can be of short duration time delay, loquitur so as to cause people
When initial voice the problem of not being recorded, cycle carries out sound prerecording in snoop procedure, can avoid the above problem.
A kind of module of automatic recording voice, including sound monitoring unit and sound recording elements, in sound monitoring unit
MCI modules are equipped with, sound monitoring unit can monitor sound and can be by intensity of sound and sound frequency to current sound
Voice identification is carried out, and can be instructed to sound recording unit sender's acoustic intelligence；Sound monitoring unit and sound recording unit
Connection, sound recording unit can carry out sound recording after receiving voice information command.
By the module of the automatic recording voice, the method that can perform a kind of automatic recording voice disclosed above is realized
The automatic identification and automatic recording of voice.
Further, sound recording unit is the sound recording unit with prerecording audio function, prerecording sound work(
Can be：It can be recycled before receiving voice information command and carry out sound prerecording, not receive voice letter in cyclic process
When breath instruction, empties the sound of a prerecording and carry out sound prerecording next time, voice letter is received in cyclic process
When breath instruction, retains the sound of prerecording and carry out sound recording.
Further, further include sound prerecording unit, sound prerecording unit connect with sound monitoring unit and can
Recipient's acoustic intelligence instructs, and sound prerecording unit, which can recycle, carries out sound prerecording, and can realize：In cyclic process not
When receiving voice information command, empties the sound of a prerecording and carry out sound prerecording next time, in cyclic process
When receiving voice information command, retain the sound of prerecording.
If starting to record after recognizing voice, people loquitur and start record voice between there are the of short duration times
Delay, the voice started when people can be caused to loquitur is not recorded, to cause lacking for voice, and sound prerecording unit
The recording of sound when achievable people loquiturs.
Further, the module can be adapted to the self-aided terminal for being equipped with HGUI clients, and the module can seal
Dress up one can dynamic load DLL, and can to HGUI clients provide interface.
Compared to the prior art the method and module of a kind of automatic recording voice of the present invention, have the advantages that：
1, voice is identified by intensity of sound and sound frequency, realizes automatic identification, automatic recording and the automatic recording of voice
Terminate, avoid manual control life record unlatching and end, can prevent record voice in there are invalid fragments or effective pieces
The problem of section missing, increases voice and records the convenience of experience, and screened by the setting of intensity of sound and sound frequency
Voice can exclude noise；
2, intensity of sound and sound frequency are default, so as to the sensitivity by changing the identification of parameter regulation voice to adapt to not
Same environment improves the robustness of voice identification.
Description of the drawings
The following further describes the present invention with reference to the drawings.
Attached drawing 1 is a kind of flow diagram of the method for 1 automatic recording voice of embodiment；
Attached drawing 2 is a kind of flow diagram of the method for 2 automatic recording voice of embodiment.
Specific implementation mode
The method and module of a kind of automatic recording voice of the present invention are made into one in the following with reference to the drawings and specific embodiments
Walk explanation.
Embodiment 1：
As shown in Fig. 1, the method for a kind of automatic recording voice of the invention, passes through intensity of sound and sound frequency automatic identification
Voice, and automatic recording voice, include the following steps：
（1）, identification voice：It records voice and preserves voice.Identification voice is, by the current sound listened to and preset sound
Intensity and sound frequency compare, if current sound meets preset intensity of sound and sound frequency, judge current sound
For voice；
（2）, record voice：After listening to voice, sound recording is automatically turned on, carries out voice recording；
（3）, preserve voice：Current sound in the predetermined amount of time listened to is made with preset intensity of sound and sound frequency
Comparison, if current sound does not meet preset intensity of sound or sound frequency, judges that current voice terminates, ends automatically sound
The voice that sound Record and Save is recorded.
Wherein, step（1）It identifies in voice step, the intensity of sound of current sound and sound frequency is compared successively
Analysis when current sound while meeting intensity of sound and the judgment criterion formula of sound frequency, judges it for voice, specially：
（1.1）, audio intensity threshold is set as unit of decibel, and set sound frequency waving interval, sound frequency wave zone
Between be 300Hz-3400Hz；
（1.2）, the current sound listened to and intensity of sound standard value compared, if the intensity of sound of current sound is less than
Or be equal to audio intensity threshold, then it is voice to judge current sound not, if the intensity of sound of current sound is more than intensity of sound
Threshold value then carries out sound frequency judgement；
（1.3）, current sound frequency and sound frequency waving interval compared, if the sound frequency of current sound not position
In sound frequency waving interval, then it is voice to judge current sound not, if the sound frequency of current sound is in sound frequency
Waving interval then judges current sound for voice.
Above-mentioned steps（1）Middle audio intensity threshold and sound frequency waving interval are believed that setting, to meet sound knowledge
It is not suitable for varying environment, sensitivity and the accuracy of voice recognition are provided.Meanwhile step（3）In, preset predetermined amount of time
It can arbitrarily be set also according to actual needs.
The beginning and end of one section of recording needs the triggering of artificial or program, terminal system can not actively monitoring arrive sound
It generates and disappears, user experience is not convenient, and there may be invalid fragments in the voice recorded, or effective voice cannot be complete
Portion is recorded.A kind of method of automatic recording voice of the present embodiment automatic identification voice and can automatically turn on voice and record, be automatic
Terminate the voice that voice Record and Save is recorded, it can the above problem.And life is screened by intensity of sound and sound frequency, it can arrange
Except noise.
Embodiment 2：
As shown in Fig. 2, in embodiment 1, start recorded voice after detecting voice, between voice detection and voice are recorded
There are of short duration time delays, i.e., start to record when people loquiturs, and the first few hundred millisecond of voice can be caused not to be recorded, from
And voice information and user experience are influenced, to solve the above problems, the present embodiment further changing on the basis of embodiment 1
Into the present embodiment is distinguished as with embodiment 1：Before recording voice, cycle carries out prescoring while identifying voice, pre-records
Sound includes：Carry out a sound prerecording at predetermined time intervals while monitoring sound, it is unidentified in cyclic process to arrive voice
When, it empties the sound of a prerecording and carries out sound prerecording next time, when recognizing voice in cyclic process, retain pre-
The sound of recording simultaneously enters recording voice step.
Wherein, in the present embodiment, carry out prescoring, every 200 milliseconds of recordings are started the cycle over while opening monitoring sound
Once；If there is no human voice signal's generation in snoop procedure, empties next 200 milliseconds last of prescoring continuation and follow
Ring；If producing human voice signal, prescoring will not be emptied and continue to record, and enter really recording step at this time.
The present embodiment realizes the whole of voice by prescoring and records, and avoids the missing of voice recording.
Embodiment 3：
A kind of module of automatic recording voice of the present invention, including sound monitoring unit and sound recording elements, sound monitoring unit
The MCI modules of c++ offers are built-in with, sound monitoring unit can monitor sound and can be by intensity of sound and sound frequency pair
Current sound carries out voice identification, and can be instructed to sound recording unit sender's acoustic intelligence；Sound monitoring unit and sound
Sound recording elements connect, and sound recording unit can carry out sound recording after receiving voice information command.
The module can be adapted to the self-aided terminal for being equipped with HGUI clients, and can be packaged into one can dynamic load
DLL, and interface can be provided to HGUI clients.
A kind of module of automatic recording voice of the present invention can be used for being assemblied in self-help tax service terminal, execute public in embodiment 1
A kind of method for the automatic identification voice opened, it is automatic to realize that voice identification and voice are recorded, and assist the self-help tax of user.
Embodiment 4：
The present embodiment is being further improved on the basis of embodiment 3, and the present embodiment is distinguished as with embodiment 3：Sound recording
Unit is the sound recording unit with prerecording audio function, and prerecording audio function is：Receiving voice information command
It can recycle before and carry out sound prerecording, when not receiving voice information command in cyclic process, empty a prerecording
Sound and carry out sound prerecording next time, when receiving voice information command in cyclic process, retain the sound of prerecording
And carry out sound recording.
A kind of method of automatic identification voice is disclosed in embodiment 1 or embodiment 2 when the present embodiment can be used for executing, automatically
It realizes that voice identification and voice are recorded, and assists the self-help tax of user.
Embodiment 5：
The present embodiment is being further improved on the basis of embodiment 3, and the present embodiment is distinguished as with embodiment 3：Further include sound
Sound prerecording unit, sound prerecording unit connect with sound monitoring unit and can the instruction of recipient's acoustic intelligence, sound pre-records
Unit processed, which can recycle, carries out sound prerecording, and can realize：When not receiving voice information command in cyclic process, empty
The sound of a upper prerecording simultaneously carries out sound prerecording next time, when receiving voice information command in cyclic process, retains
The sound of prerecording.
A kind of method of automatic identification voice is disclosed in embodiment 1 or embodiment 2 when the present embodiment can be used for executing, automatically
It realizes that voice identification and voice are recorded, and assists the self-help tax of user.
The technical personnel in the technical field can readily realize the present invention with the above specific embodiments,.But it answers
Work as understanding, the present invention is not limited to above-mentioned specific implementation modes.On the basis of the disclosed embodiments, the technical field
Technical staff can arbitrarily combine different technical features, to realize different technical solutions.Except the technology described in specification
It is the known technology of those skilled in the art outside feature.
Claims (8)
1. a kind of method of automatic recording voice, it is characterised in that by intensity of sound and sound frequency automatic identification voice, and
Automatic recording voice, including：
Identify voice：The current sound listened to and preset intensity of sound and sound frequency are compared, if current sound
Meet preset intensity of sound and sound frequency, then judges current sound for voice；
Record voice：After listening to voice, sound recording is automatically turned on, carries out voice recording；
Preserve voice：Current sound in the predetermined amount of time listened to is opposed with preset intensity of sound and sound frequency
Than if current sound does not meet preset intensity of sound or sound frequency, judging that current voice terminates, ending automatically sound
The voice that Record and Save is recorded.
2. a kind of method of automatic recording voice according to claim 1, it is characterised in that identification voice includes following step
Suddenly：
Audio intensity threshold is set as unit of decibel, and sets sound frequency waving interval；
The current sound listened to and intensity of sound standard value are compared, if the intensity of sound of current sound is strong more than sound
Threshold value is spent, then carries out sound frequency judgement；
Current sound frequency and sound frequency waving interval are compared, if the sound frequency of current sound is in sound audio
Rate waving interval then judges current sound for voice.
3. a kind of method of automatic recording voice according to claim 2, it is characterised in that sound frequency waving interval is set
It is set to 300Hz-3400Hz.
4. a kind of method of automatic recording voice according to claim 1,2 or 3, it is characterised in that before recording voice,
Cycle carries out prescoring while identifying voice, and prescoring includes：One is carried out at predetermined time intervals while monitoring sound
Secondary sound prerecording, in cyclic process it is unidentified to voice when, empty the sound of a prerecording and carry out sound next time
Prerecording when recognizing voice in cyclic process, retains the sound of prerecording and enters and record voice step.
5. a kind of module of automatic recording voice, it is characterised in that including sound monitoring unit and sound recording elements, sound prison
Unit is listened to be built-in with MCI modules, sound monitoring unit can monitor sound and can be by intensity of sound and sound frequency to working as
Preceding sound carries out voice identification, and can be instructed to sound recording unit sender's acoustic intelligence；Sound monitoring unit and sound
Recording elements connect, and sound recording unit can carry out sound recording after receiving voice information command.
6. a kind of module of automatic recording voice according to claim 5, it is characterised in that sound recording unit be with
The sound recording unit of prerecording audio function, prerecording audio function are：It can be followed before receiving voice information command
Ring carries out sound prerecording, and when not receiving voice information command in cyclic process, the sound for emptying a prerecording is gone forward side by side
Capable sound prerecording next time, when receiving voice information command in cyclic process, retains the sound of prerecording and carries out sound
It records.
7. a kind of module of automatic recording voice according to claim 5, it is characterised in that further include sound prerecording list
Member, sound prerecording unit connect with sound monitoring unit and can recipient's acoustic intelligence instruction, sound prerecording unit can
Cycle carries out sound prerecording, and can realize：When not receiving voice information command in cyclic process, empties one and pre-record
The sound of system simultaneously carries out sound prerecording next time, when receiving voice information command in cyclic process, retains the sound of prerecording
Sound.
8. a kind of module of automatic recording voice according to claim 5,6/7, it is characterised in that the module can fit
With the self-aided terminal for being equipped with HGUI clients, and the module can be packaged into one can dynamic load DLL, and can be to
HGUI clients provide interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810001321.1A CN108364663A (en) | 2018-01-02 | 2018-01-02 | A kind of method and module of automatic recording voice |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810001321.1A CN108364663A (en) | 2018-01-02 | 2018-01-02 | A kind of method and module of automatic recording voice |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108364663A true CN108364663A (en) | 2018-08-03 |
Family
ID=63011001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810001321.1A Pending CN108364663A (en) | 2018-01-02 | 2018-01-02 | A kind of method and module of automatic recording voice |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108364663A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110970054A (en) * | 2019-11-06 | 2020-04-07 | 广州视源电子科技股份有限公司 | Method and device for automatically stopping voice acquisition, terminal equipment and storage medium |
| CN111583898A (en) * | 2020-05-26 | 2020-08-25 | 舒伟伟 | Space environment multi-directional selective noise reduction system and method |
| CN111613252A (en) * | 2020-04-29 | 2020-09-01 | 广州三人行壹佰教育科技有限公司 | Audio recording method, device, system, equipment and storage medium |
| CN112786047A (en) * | 2021-01-28 | 2021-05-11 | 百度在线网络技术（北京）有限公司 | Voice processing method, device, equipment, storage medium and intelligent sound box |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080077403A1 (en) * | 2006-09-22 | 2008-03-27 | Fujitsu Limited | Speech recognition method, speech recognition apparatus and computer program |
| CN101211615A (en) * | 2006-12-31 | 2008-07-02 | 于柏泉 | Method, system and apparatus for automatic recording for specific human voice |
| US20110135152A1 (en) * | 2009-12-08 | 2011-06-09 | Akifumi Kashiwagi | Information processing apparatus, information processing method, and program |
| CN102647525A (en) * | 2012-04-16 | 2012-08-22 | 中兴通讯股份有限公司 | Mobile terminal and processing method on abnormal communication of mobile terminal |
| WO2012137263A1 (en) * | 2011-04-08 | 2012-10-11 | 三菱電機株式会社 | Voice recognition device and navigation device |
| CN104539793A (en) * | 2014-12-15 | 2015-04-22 | 深圳市金立通信设备有限公司 | Terminal |
| CN106131287A (en) * | 2016-07-13 | 2016-11-16 | 奇酷互联网络科技（深圳）有限公司 | Call recording method, device and communication terminal |
| CN107181849A (en) * | 2017-04-19 | 2017-09-19 | 北京小米移动软件有限公司 | The way of recording and device |
| CN107274916A (en) * | 2012-12-05 | 2017-10-20 | 北京三星通信技术研究有限公司 | The method and device operated based on voiceprint to audio/video file |
-
2018
- 2018-01-02 CN CN201810001321.1A patent/CN108364663A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080077403A1 (en) * | 2006-09-22 | 2008-03-27 | Fujitsu Limited | Speech recognition method, speech recognition apparatus and computer program |
| US8768692B2 (en) * | 2006-09-22 | 2014-07-01 | Fujitsu Limited | Speech recognition method, speech recognition apparatus and computer program |
| CN101211615A (en) * | 2006-12-31 | 2008-07-02 | 于柏泉 | Method, system and apparatus for automatic recording for specific human voice |
| US20110135152A1 (en) * | 2009-12-08 | 2011-06-09 | Akifumi Kashiwagi | Information processing apparatus, information processing method, and program |
| WO2012137263A1 (en) * | 2011-04-08 | 2012-10-11 | 三菱電機株式会社 | Voice recognition device and navigation device |
| CN102647525A (en) * | 2012-04-16 | 2012-08-22 | 中兴通讯股份有限公司 | Mobile terminal and processing method on abnormal communication of mobile terminal |
| CN107274916A (en) * | 2012-12-05 | 2017-10-20 | 北京三星通信技术研究有限公司 | The method and device operated based on voiceprint to audio/video file |
| CN104539793A (en) * | 2014-12-15 | 2015-04-22 | 深圳市金立通信设备有限公司 | Terminal |
| CN106131287A (en) * | 2016-07-13 | 2016-11-16 | 奇酷互联网络科技（深圳）有限公司 | Call recording method, device and communication terminal |
| CN107181849A (en) * | 2017-04-19 | 2017-09-19 | 北京小米移动软件有限公司 | The way of recording and device |
Non-Patent Citations (1)
| Title |
|---|
| 王珏，石宝峰著: "《影视录音工艺与技巧》", 30 November 2016 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110970054A (en) * | 2019-11-06 | 2020-04-07 | 广州视源电子科技股份有限公司 | Method and device for automatically stopping voice acquisition, terminal equipment and storage medium |
| CN111613252A (en) * | 2020-04-29 | 2020-09-01 | 广州三人行壹佰教育科技有限公司 | Audio recording method, device, system, equipment and storage medium |
| CN111583898A (en) * | 2020-05-26 | 2020-08-25 | 舒伟伟 | Space environment multi-directional selective noise reduction system and method |
| CN112786047A (en) * | 2021-01-28 | 2021-05-11 | 百度在线网络技术（北京）有限公司 | Voice processing method, device, equipment, storage medium and intelligent sound box |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108364663A (en) | A kind of method and module of automatic recording voice | |
| CN104102181B (en) | Intelligent home control method, device and system | |
| US20140078404A1 (en) | Method and system for automatically adjusting television volume, television set and television remote controller | |
| US6236970B1 (en) | Adaptive speech rate conversion without extension of input data duration, using speech interval detection | |
| CN109817211B (en) | Electric appliance control method and device, storage medium and electric appliance | |
| CN106214436A (en) | A kind of intelligent blind guiding system based on mobile phone terminal and blind-guiding method thereof | |
| CN109256134A (en) | A kind of voice awakening method, storage medium and terminal | |
| CN105430316B (en) | Trial video automatic control system and method | |
| CN107562403A (en) | A kind of volume adjusting method, smart machine and storage medium | |
| CN109697989B (en) | Audio data processing method, server and readable storage medium | |
| US20200251120A1 (en) | Method and system for individualized signal processing of an audio signal of a hearing device | |
| CN106921911A (en) | Voice acquisition method and device | |
| CN111833902A (en) | Awakening model training method, awakening word recognition device and electronic equipment | |
| CN103327433A (en) | Audio input interface detection method and system thereof | |
| CN112002315A (en) | Voice control method and device, electrical equipment, storage medium and processor | |
| CN106493747B (en) | A kind of method of intelligent robot from turn manual service | |
| JP2009122598A (en) | Electronic device, control method of electronic device, speech recognition device, speech recognition method and speech recognition program | |
| CN104580714A (en) | Terminal | |
| CN111199751B (en) | Microphone shielding method and device and electronic equipment | |
| CN110211319B (en) | Security monitoring early warning event tracking method and system | |
| CN112438665B (en) | Off-home mode sweeping method of sweeper and sweeper | |
| CN112283776A (en) | Range hood control method and device, range hood and readable storage medium | |
| CN106656688A (en) | Noise processing method and apparatus | |
| CN108735234A (en) | A kind of device monitoring health status using voice messaging | |
| CN113934926A (en) | Recommendation method and device for interactive scene and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180803 |
|
| RJ01 | Rejection of invention patent application after publication |