CN207718803U - Multiple source speech differentiation identifying system - Google Patents
Multiple source speech differentiation identifying system Download PDFInfo
- Publication number
- CN207718803U CN207718803U CN201721684036.1U CN201721684036U CN207718803U CN 207718803 U CN207718803 U CN 207718803U CN 201721684036 U CN201721684036 U CN 201721684036U CN 207718803 U CN207718803 U CN 207718803U
- Authority
- CN
- China
- Prior art keywords
- audio processing
- microphone
- identifying system
- voice
- multiple source
- 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.)
- Expired - Fee Related
Links
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The utility model discloses a kind of multiple source speech differentiation identifying systems, including at least two-way audio processing module, for being connect with microphone；Computer equipment, includes the sound identification module for speech recognition, and the sound identification module distinguishes voice source according to the hardware identifier obtained from the audio processing modules, and by after speech recognition content of text and corresponding voice source associated record.The utility model can be under unmanned intervention or operation, when solving synchronous more people in same computer equipment or asynchronous talk, automatically by speech-to-text, it is correct to distinguish voice source, the content of text of automatic corresponding output information source, reduces manual operation, reduces the labor intensity of staff to greatest extent, it has ensured the objective of voice content, has improved whole work efficiency.
Description
Technical field
The utility model is related to voice sources to identify field, more particularly to a kind of multiple source speech differentiation identifying system.
Background technology
In recent years, as speech ciphering equipment and intelligent sound turn the extensive implementation of text technology, scene has been pushed to handle a case (live
Office, meeting) work such as dialogue are intelligent.However, can not realize that the more people of differentiation are same based on current speech ciphering equipment and software
When speech-to-text, dependence is traditional artificial input mode, and implementation process is complicated, inefficiency.
When carrying out text entry using speech ciphering equipment or software, information source differentiation is artificially to switch, and is caused in recording process
Occur accidentally recording, especially in the case where working long hours, staff is in fatigue conditions, can accurately less distinguish information source
Speech content.It is modified moreover, staff may be added in the opinion and sentence of oneself, thus causes accurately to reflect and work as
When session operational scenarios, influence the authenticity of text record content.
It is based on personal or interactive intelligent language mostly when turning word equipment or software using existing intelligent sound
Sound turns text technology realization, because multiple source either synchronously or asynchronously carries out voice dialogue, sound overlapping makes software that information source cannot be distinguished
Respective voice content.Cause to fail to automatically record complete writing record by manual confirmation information.
Utility model content
Above-mentioned at least one in order to solve the problems, such as, the utility model provides a kind of completely new more voice automatic identification letter
Source technology method.
One according to the present utility model embodiment there is provided a kind of multiple source speech differentiation identifying systems, including：
At least two-way audio processing module, for being connect with microphone；
Computer equipment, includes the sound identification module for speech recognition, and the sound identification module is according to from described
Audio processing modules obtain hardware identifier distinguish voice source, and by after speech recognition content of text and corresponding voice
Information source associated record.
In above-mentioned multiple source speech differentiation identifying system, the sound identification module includes priority setup module,
Priority for the information source that voice is arranged.
In above-mentioned multiple source speech differentiation identifying system, the audio processing modules are that have processing audio data energy
Power and the module with ability to communicate.
In above-mentioned multiple source speech differentiation identifying system, the audio processing modules include USB sound cards, PCI-E sound
Card and/or microcontroller sound card.
Further include USB deconcentrators in above-mentioned multiple source speech differentiation identifying system, for connecting the USB sound cards
It is connected to the computer equipment.
In above-mentioned multiple source speech differentiation identifying system, at least two-way audio processing module includes built-in audio
Processing module and/or external audio processing modules, and the built-in audio processing module is arranged in the computer equipment.
In above-mentioned multiple source speech differentiation identifying system, the computer equipment is portable computer, desk-top meter
Calculation machine, mobile terminal or industrial PC.
Further include multiple microphones in above-mentioned multiple source speech differentiation identifying system, the multiple microphone includes
Wire microphone and/or wireless microphone.
In above-mentioned multiple source speech differentiation identifying system, the audio processing modules include microphone wireless receiver
And/or wire microphone interface.
In above-mentioned multiple source speech differentiation identifying system, the wireless microphone includes 2.4G wireless transmitter modules；
The microphone wireless receiver includes 2.4G wireless receiving modules.
Multiple source speech differentiation identifying system provided by the utility model can automatically distinguish multiple source voice pair in real time
It talks about and voice is converted to the text information described in corresponding information source, when record can not have to manpower intervention, not only reduce labour
Power is put into, and greatly improves the working efficiency of typing, and solving when staff works overloadingly for a long time leads to pen
There is the situation of mistake in record.
Moreover, the multiple source speech differentiation identifying system of the utility model uses MCVF multichannel voice frequency processing module, voice is known
Other module distinguishes voice source according to the hardware identifier that is obtained from each audio processing modules, and by the text after speech recognition
Content is associatedly recorded with corresponding voice source, therefore, it is possible to intelligent positioning speech information source, precisely inputs spokesman's dialogue
Content.
Since the discrimination of multiple source speech differentiation identifying system provided by the utility model is high, different languages can be distinguished
Therefore message source can restore full dialog content, ensure that voice record integrality, slitless connection are also just reduced artificial certainly
Word modification, ensured speech authenticity.
In addition, there is no audio processing modules in computer equipment or only there are one when audio processing modules, being utilized outside
Audio processing modules are set, and external audio processing modules are attached with computer equipment by USB interface or communication interface,
Therefore, can not do the transformation on hardware to existing computer equipment can also realize multiple source speech differentiation.Due to can be with
It is connect with external audio processing modules using USB interface, has greatly expanded the multiple source speech differentiation identification of the utility model
The applicable region of system and applicable equipment are having even if in remote districts or only the local of limited hardware condition
The system that the utility model can be easily applied.
The multiple source speech differentiation identifying system of the utility model can simplify computer operation it is more intelligent, human nature
The advantages that change, substantially increase voice source identification automatization level, can be widely used for the administration of justice, law enforcement, government affairs, commercial affairs,
The work such as the medical consultation of doctors, minutes, teaching simplify and facilitate the subsequent routine work of the work such as judicial, law enforcement, have
Improve work efficiency to effect.
Description of the drawings
It, below will be to attached drawing needed in the embodiment in order to illustrate more clearly of the technical solution of the utility model
It is briefly described, it should be understood that the following drawings illustrates only some embodiments of the utility model, therefore is not construed as
Restriction to scope of protection of the utility model.
Fig. 1 is the schematic diagram of one embodiment of the multiple source speech differentiation identifying system of the utility model.
Main element symbol description：
100- computer equipments；
110- sound identification modules；
120- built-in audio processing modules；
The external audio processing modules of 130-；
140- microphones.
Specific implementation mode
To make the purpose of this utility model, technical solution and advantage be more clearly understood, combines implement referring to the drawings
The utility model is further described in example.
Hereinafter, the various embodiments of the utility model will be described more fully.The utility model can have various realities
Example is applied, and can adjust and change wherein.It should be understood, however, that：There is no limit the various embodiments of the utility model
In the intention of specific embodiment disclosed herein, but the utility model should be interpreted as covering falling into the various of the utility model
All adjustment, equivalent and/or alternative in the spirit and scope of embodiment.
Hereinafter, the term " comprising " that can be used in the various embodiments of the utility model or " may include " indicate institute
Disclosed function, operation or the presence of element, and the increase of one or more functions, operation or element is not limited.In addition,
As used in the various embodiments of the utility model, term " comprising ", " having " and its cognate are meant only to indicate specific
Feature, number, step, operation, the combination of element, component or aforementioned item, and be understood not to exclude one or first
A number of other features, number, step, operation, the presence of the combination of element, component or aforementioned item or one or more spies of increase
Sign, number, step, the possibility of operation, the combination of element, component or aforementioned item.
In the various embodiments of the utility model, statement " A or/and B " includes any combinations of the word listed file names with
Or all combinations, such as, it may include A, B and A and B both.
The statement (" first ", " second " etc.) used in the various embodiments of the utility model can be modified various
Various constituent element in embodiment, but respective sets can not be limited into element.For example, presented above be not intended to limit the element
Sequence and/or importance.The purpose presented above for being only used for differentiating an element and other elements.For example, first uses
Family device and second user device indicate different user device, although the two is all user apparatus.For example, not departing from this practicality
In the case of the range of novel various embodiments, first element is referred to alternatively as second element, and similarly, second element also can quilt
Referred to as first element.
It should be noted that：In the present invention, unless otherwise specific regulation and definition, " installation ", " connection ", " fixation "
Equal terms shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection or being integrally connected；It can be with
It is mechanical connection, can also be electrical connection；Can be directly connected to, and it can be indirectly connected through an intermediary；Can be
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood as the case may be
Concrete meaning in the present invention.
The term used in the various embodiments of the utility model is used only for the purpose of describing specific embodiments and simultaneously
It is not intended to the various embodiments of limitation the utility model.Unless otherwise defined, otherwise all terms used herein (including skill
Art term and scientific terminology) have and the various embodiment one skilled in the art of the utility model are normally understood contains
The identical meaning of justice.The term (term such as limited in the dictionary generally used) be to be interpreted as have to related
The identical meaning of situational meaning in technical field and containing for Utopian meaning or too formal will be interpreted as having
Justice, unless being clearly defined in the various embodiments of the utility model.
To solve above-mentioned at least one technical problem, an embodiment of the utility model provides a kind of multiple source voice
Division identification system, can during more people's simultaneous voices, accurately recording voice message source and realize accurately, it is real
Time zone component source.In the completely new solution, in computer equipment connection at least two-way audio processing module, in each sound
A wired or wireless microphone is connected respectively in frequency processing module, sound is received by microphone and is transferred to respectively
Audio processing modules.
Since voice messaging is transferred to computer by different audio processing modules, the real-time multiple source voice on computer
Division identification system can position voice messaging using audio processing modules；In order to automatically record every section of language in voice process
Sound content achievees the effect that intelligent processing text information.The electronic record of the utility model is passed through by multiple microphones
Multiple audio processing modules collect the sound from various information source, and are converted into corresponding word by sound identification module,
It is recorded on text box, discrimination is very high.For example, two microphones A, B and two-way audio processing module A, B, A information sources are said
When you are good, " A information sources can be shown on text box：Hello "；Then, when B information sources and then say that you are good, " B can be shown on text box
Information source：Hello ".Certainly, the utility model is not limited to two microphones of A, B and two-way audio processing module, it may be possible to more
A microphone and more multichannel audio processing modules.
In addition, it is contemplated that it is possible that sound overlaps situation, multiple source speech differentiation identification system in such as Interrogation Procedure
System can also set voice source priority, avoid occurring sound coincidence in Interrogation Procedure and can not determining voice messaging
Source eventually leads to the situation that text message causes confusion during voice source is distinguished.
Fig. 1 shows the schematic structure of one embodiment of the multiple source speech differentiation identifying system of the utility model
Figure.
A kind of multiple source speech differentiation identifying system in Fig. 1, including：Microphone 140, for handling voice；Built-in sound
Frequency processing module 120 and external audio processing modules 130, connect correspondingly with microphone 140；Computer equipment 100, packet
Include the sound identification module 110 for speech recognition, the sound identification module 110 is according to from built-in audio processing module 120
With external audio processing modules 130 obtain hardware identifier distinguish voice source, and by after speech recognition content of text with
Corresponding voice source associatedly records.Although including microphone in the multiple source speech differentiation identifying system of Fig. 1,
The multiple source speech differentiation identifying system of the utility model can not include microphone, at this point, microphone can as with this reality
The extra members being used cooperatively with novel multiple source speech differentiation identifying system.
Microphone 140 can use wire microphone or wireless microphone, it is of course also possible to use wire microphone simultaneously
And wireless microphone.External audio processing modules 130 and microphone 140 connect by a dotted line in Fig. 1, and expression passes through between the two
Wireless mode connects.Certainly, microphone 140 can also be handled by radio connection (such as bluetooth approach) and built-in audio
Module 120 connects.
When using wire microphone, the wire microphone interface on external audio processing modules 130 can be wired to.
External audio processing modules 130 can also include microphone wireless receiver, for connecting wireless microphone.
Therefore, may include on external audio processing modules 130 microphone wireless receiver, wire microphone interface,
Or both microphone wireless receiver and wire microphone interface.
When using wireless microphone, wireless microphone may include 2.4G wireless transmitter modules, microphone wireless receiving
Device may include 2.4G wireless receiving modules.
2.4G wireless modules are operated in the whole world and exempt to apply within the scope of ISM channels 2400M-2483M, realize booting automatic frequency sweep
Function shares 50 working channels, can work at the same time in same occasion for 50 users, manually be assisted without using person simultaneously
It adjusts, configurating channel.Audio processing modules and wireless microphone can also carry out the transmission of audio data for example, by bluetooth.
Although be shown in Fig. 1 simultaneously include built-in audio processing module 120 and external audio processing modules 130, when
It so, can also be all using built-in audio processing module or all using external audio processing modules.Audio processing modules can wrap
Include sound card.Sound card is also audio card, is component part most basic in multimedia technology, is to realize that sound wave/word signal mutually turns
A kind of hardware changed.Sound card can be PCI-E sound cards, USB sound cards, microcontroller sound card etc..External audio processing modules and built-in
Audio processing modules are that the original sound signal from microphone 140 is converted, and are exported to sound identification module 110.
Sound identification module 110 in the utility model is converted to the audio signal that microphone 140 obtains accordingly
Text message.
Sound identification module 110 needs to utilize speech recognition technology, also referred to as automatic speech recognition (ASR), target
Be vocabulary Content Transformation in the voice by the mankind it is computer-readable input, such as button, binary coding or character
Sequence.
Speech recognition may include two stages：Training and identification.Training and identification can pre-process input voice
And feature extraction.The specific works that training stage is done can collect a large amount of voice language material, be carried by pretreatment and feature
Character vector is obtained after taking, and the reference model library for establishing training voice is achieved the purpose that finally by feature modeling.And know
The groundwork that the other stage is done may include to input the reference model in the character vector and reference model library of voice into
Row similarity measurement compares, and is then exported using the highest input feature vector vector of similitude as recognition result.In this way, finally just reaching
The purpose of speech recognition is arrived.Sound identification module 110 can be the module after training.
Speech recognition in the utility model is the identification for unspecified person, that is, identification object is for different
Personnel.Therefore, sound identification module 110 can handle the voice of more people and record and train, and by study, can reach very high
Discrimination.
The software or can be meter that sound identification module 110 can be stored on the memory of computer equipment 100
Calculate the hardware circuit inside machine equipment 100.
Can be a kind of mould based on Embedded speech recognition technology when sound identification module 110 is hardware circuit
Block, it may include voice recognition chip and some other accessory circuits, main control chip that can easily with computer equipment 100
It is communicated.
Due to when scene is handled a case, medical treatment is held a consultation, it is often necessary to which mobile office, therefore, computer equipment 100 is preferably
Portable computer etc. is moved easily the computer equipment of office.
Computer equipment 100 may include multiple USB interfaces or other communication interfaces (such as bluetooth communication interface), can be with
It is connected one to one with each external audio processing modules 130 by each USB interface on computer equipment 100.Voice is known
Other module 110 can determine the source of voice messaging according to corresponding external audio processing modules 130.
It, can not be directly same in addition, the USB interface in computer equipment 100 is less, such as only there are one when USB interface
When connecting multiple external audio processing modules 130, can be transferred using USB deconcentrators (not shown).USB deconcentrators
It is directly connected to computer equipment 100, external audio processing modules 130 can be connected to USB deconcentrators.
It is multiple that USB deconcentrators (USB Hub) refer to that a USB interface can be extended to by one kind, and can make these
Interface device used at the same time.USB HUB according to affiliated usb protocol can be divided into such as USB2.0HUB, USB3.0HUB with
USB3.1HUB。
External audio processing modules 130 connect outer, external audio frequency process except through USB interface with computer equipment 100
Module 130 can also be connect by other interface modes with computer equipment 100, such as pass through the wireless connections such as bluetooth, WiFi
Mode.
Multiple source speech differentiation identifying system preferably further includes photographing module, for handling image, can handled in this way
Related image information is collected while audio.Camera can be separately provided, and can also be arranged on computer equipment 100.
In addition, sound identification module 110 may include priority setup module, the source for the predicate sound to be arranged
Priority.For example, can be by the way that the top grade of multiple microphones 140, the priority of audio processing modules or corresponding USB be arranged
The priority in voice source is arranged in the priority of interface, can be arranged according to the unique identification information of above-mentioned each hardware.It is real
It is the priority setting that the voice handled for multiple microphones 140 carries out speech recognition in matter.
For example, being connected to two audio processing modules A and B on computer equipment 100, two microphone A ' are connected respectively
With B ' (audio processing modules and microphone are corresponding), in two people respectively to microphone A ' and B ' while when talking, two sound
It passes equipment back simultaneously, if the voice messaging of two people identified, does not know the placement location of two identification texts,
Identification information may be caused chaotic.
If audio processing modules A is set to high priority by priority setup module, in audio frequency process mould
When block A and B obtains voice simultaneously, speech recognition that can be with automatic time delay to the audio processing modules B microphone B ' received.
It should be noted that above-mentioned gives up the identification to the voice acquired in audio processing modules B being only delayed,
Rather than give up the preservation to the audio.
In addition, if it is high priority that audio processing modules A, which is arranged, by priority setup module, in audio frequency process
When modules A and B obtain voice simultaneously, can also the voice of audio processing modules A and B be all subjected to speech recognition, after recognition
Before the Classical correlation text of audio processing modules A being placed on, the Classical correlation text of audio processing modules B is placed on
Afterwards, it is used in combination bracket to mark.
In Fig. 1, microphone 140 passes through built-in audio processing module 120 and external audio processing modules 130 and computer
Equipment 100 is connected, but multiple microphones 140 can also all with built-in audio processing module or all with external audio frequency process
Module connects correspondingly.
Hardware identifier in the utility model can be for example external and/or built-in audio processing module mark, with it is each
The identifying of microphone of audio processing modules connection, the USB interface of external audio processing modules connection mark etc..It is preferred that using
The hardware identifier of audio processing modules.
Three groups of audio processing modules and microphone 140 are shown in Fig. 1, however, the utility model is without being limited thereto, it can also
The audio processing modules and microphone 140 organized including two groups or more.
In addition, although the utility model is related to multiple source speech differentiation identifying system, it is clear that can be used for one
Speech recognition, at this time, it is only necessary to an audio processing modules and a microphone.If computer equipment itself includes interior
Audio processing modules are set, at this point, the microphone can also be connect with the built-in audio processing module of computer equipment 100.
The utility model discloses a kind of multiple voice source identifying systems, including at least two-way audio processing module, make
For the middleware being connect with computer equipment, computer includes but are not limited to support speech-to-text module, computer according to
The hardware identifier automatic distinguishing voice source obtained from the audio processing modules, and corresponding voice signal is obtained, simultaneously
Content of text after speech recognition turns word and corresponding voice source associated record.The utility model can be dry at nobody
Under pre- or operation, when solving synchronous more people in same computer equipment or asynchronous talk, automatically by speech-to-text, correctly
Voice source is distinguished, the content of text of automatic corresponding output information source reduces manual operation, reduces the labor of staff to greatest extent
Fatigue resistance has ensured the objective of voice content, improves whole work efficiency.
By above-mentioned multiple source speech differentiation identifying system, the utility model can solve to handle a case at the scene, inquest, take charge of
Method, law enforcement, government affairs, commercial affairs, the medical treatment consultation of doctors, teaching etc. are under environment, can be with intelligence with this system under multi-person speech session operational scenarios
Voice source can be distinguished, and positioning, mark are made to every section of voice, and its content is switched into word automatically, in order in voice
Every section of voice content is automatically recorded in the process, avoids the manual operation that staff modifies in record, reaches intelligence
Change the effect of processing voice content.
In addition, during use, inevitably it is in the presence of that sound coincidence, the multiple source speech differentiation of the utility model identify
System can also set priority, and the voice signal of automatic identification priority level avoids sound occur in more voice identification process
Sound overlaps and can not determine voice messaging source, eventually leads to the situation that text message during voice dialogue causes confusion.
It should be noted that the term " computer equipment " referred in the utility model is also a sensu lato term,
Can be for example server, PC, laptop, industrial PC, mobile terminal (such as tablet computer, mobile phone,
Ipad) etc..
The above is only the preferred embodiment of the utility model only, is not intended to limit the utility model, all at this
Within the spirit and principle of utility model, any modification, equivalent substitution, improvement and etc. done should be included in the utility model
Within the scope of protection.
Claims (10)
1. a kind of multiple source speech differentiation identifying system, which is characterized in that including：
At least two-way audio processing module, for being connect with microphone；
Computer equipment, includes the sound identification module for speech recognition, and the sound identification module is according to from the audio
Processing module obtain hardware identifier distinguish voice source, and by after speech recognition content of text and corresponding voice source
Associated record.
2. multiple source speech differentiation identifying system according to claim 1, it is characterised in that：
The sound identification module includes priority setup module, the priority of the information source for voice to be arranged.
3. multiple source speech differentiation identifying system according to claim 1, it is characterised in that：
The audio processing modules are that have processing audio data ability and the module with ability to communicate.
4. multiple source speech differentiation identifying system according to claim 3, it is characterised in that：
The audio processing modules include USB sound cards, PCI-E sound cards and/or microcontroller sound card.
5. multiple source speech differentiation identifying system according to claim 4, it is characterised in that：
Further include USB deconcentrators, for the USB sound cards to be connected to the computer equipment.
6. multiple source speech differentiation identifying system according to claim 1, it is characterised in that：
At least two-way audio processing module includes built-in audio processing module and/or external audio processing modules, and institute
Built-in audio processing module is stated to be arranged in the computer equipment.
7. multiple source speech differentiation identifying system according to claim 1, it is characterised in that：
The computer equipment is portable computer, desktop computer, mobile terminal or industrial PC.
8. multiple source speech differentiation identifying system according to claim 1, it is characterised in that：
Further include multiple microphones, the multiple microphone includes wire microphone and/or wireless microphone.
9. multiple source speech differentiation identifying system according to claim 8, it is characterised in that：
The audio processing modules include microphone wireless receiver and/or wire microphone interface.
10. multiple source speech differentiation identifying system according to claim 9, it is characterised in that：
The wireless microphone includes 2.4G wireless transmitter modules；
The microphone wireless receiver includes 2.4G wireless receiving modules.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201721684036.1U CN207718803U (en) | 2017-12-06 | 2017-12-06 | Multiple source speech differentiation identifying system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201721684036.1U CN207718803U (en) | 2017-12-06 | 2017-12-06 | Multiple source speech differentiation identifying system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN207718803U true CN207718803U (en) | 2018-08-10 |
Family
ID=63059760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201721684036.1U Expired - Fee Related CN207718803U (en) | 2017-12-06 | 2017-12-06 | Multiple source speech differentiation identifying system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN207718803U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107910006A (en) * | 2017-12-06 | 2018-04-13 | 广州宝镜智能科技有限公司 | Audio recognition method, device and multiple source speech differentiation identifying system |
| CN110797043A (en) * | 2019-11-13 | 2020-02-14 | 苏州思必驰信息科技有限公司 | Conference voice real-time transcription method and system |
| CN111833899A (en) * | 2020-07-27 | 2020-10-27 | 腾讯科技（深圳）有限公司 | Voice detection method based on multiple sound zones, related device and storage medium |
-
2017
- 2017-12-06 CN CN201721684036.1U patent/CN207718803U/en not_active Expired - Fee Related
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107910006A (en) * | 2017-12-06 | 2018-04-13 | 广州宝镜智能科技有限公司 | Audio recognition method, device and multiple source speech differentiation identifying system |
| CN110797043A (en) * | 2019-11-13 | 2020-02-14 | 苏州思必驰信息科技有限公司 | Conference voice real-time transcription method and system |
| CN110797043B (en) * | 2019-11-13 | 2022-04-12 | 思必驰科技股份有限公司 | Conference voice real-time transcription method and system |
| CN111833899A (en) * | 2020-07-27 | 2020-10-27 | 腾讯科技（深圳）有限公司 | Voice detection method based on multiple sound zones, related device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106104569B (en) | For establishing the method and apparatus of connection between electronic device | |
| CN108427910B (en) | Deep neural network AR sign language translation learning method, client and server | |
| CN103745722B (en) | Voice interaction smart home system and voice interaction method | |
| CN207718803U (en) | Multiple source speech differentiation identifying system | |
| CN107910006A (en) | Audio recognition method, device and multiple source speech differentiation identifying system | |
| CN104538034A (en) | Voice recognition method and system | |
| CN109032039A (en) | A kind of method and device of voice control | |
| CN113297843B (en) | Reference resolution method and device and electronic equipment | |
| CN106022208A (en) | Human body motion recognition method and device | |
| CN106875939A (en) | To the Chinese dialects voice recognition processing method and intelligent robot of wide fluctuations | |
| CN107862071A (en) | The method and apparatus for generating minutes | |
| CN108334498A (en) | Method and apparatus for handling voice request | |
| CN109660865A (en) | Make method and device, medium and the electronic equipment of video tab automatically for video | |
| WO2023272616A1 (en) | Text understanding method and system, terminal device, and storage medium | |
| CN108510988A (en) | A kind of speech recognition system and method for deaf-mute | |
| CN104361787A (en) | System and method for converting signals | |
| CN111160047A (en) | Data processing method and device and data processing device | |
| WO2021179703A1 (en) | Sign language interpretation method and apparatus, computer device, and storage medium | |
| KR20150135688A (en) | A memory aid method using audio-visual data | |
| CN105786378B (en) | A kind of method and apparatus scaling foul papers interface | |
| CN109087646A (en) | A kind of importing artificial intelligence is ultra-deep to be learnt to know method for distinguishing for phonetic image | |
| CN109871128B (en) | Question type identification method and device | |
| KR20190025261A (en) | Conversion service system and its method in real-time automatic programming language based on natural language speech recognition | |
| CN110781861A (en) | Electronic equipment and method for universal object recognition | |
| CN107316644A (en) | Method and device for information exchange |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180810 Termination date: 20201206 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |