CN109785864A - Eliminate the method and device of court's trial noise jamming - Google Patents
Eliminate the method and device of court's trial noise jamming Download PDFInfo
- Publication number
- CN109785864A CN109785864A CN201910140271.XA CN201910140271A CN109785864A CN 109785864 A CN109785864 A CN 109785864A CN 201910140271 A CN201910140271 A CN 201910140271A CN 109785864 A CN109785864 A CN 109785864A
- Authority
- CN
- China
- Prior art keywords
- microphone
- group
- volume
- sound
- noise threshold
- 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.)
- Granted
Links
Landscapes
- Circuit For Audible Band Transducer (AREA)
Abstract
The invention discloses a kind of method and devices for eliminating court's trial noise jamming, this method comprises: the sound of court's trial scene multichannel microphone is acquired, wherein having a noise threshold per microphone preset all the way;The volume of multichannel microphone is compared with corresponding noise threshold, if the volume of microphone is higher than corresponding noise threshold, the sound of the microphone is then sent to speech recognition system, if the volume of microphone is lower than corresponding noise threshold, silence processing is carried out to the microphone.The present invention preferably protects primary sound; noise is only subjected to silence processing, i.e., the sound of the sound and adjacent teller that feed back to sound equipment or power amplifier carries out silence processing; the noise jamming in court trial process is eliminated, speech recognition system is avoided to identify the unwanted text of some reality.
Description
Technical field
The present invention relates to technical field of voice recognition more particularly to a kind of method and devices for eliminating court's trial noise jamming.
Background technique
When law court tries case, clerk is needed to record the speech content of each role.With artificial intelligence
Development, speech recognition technology is more and more mature, and speech recognition system can accomplish very high correct recognition rata, complete to it
After face is promoted, the workload of clerk can be greatly reduced.But at present in court's trial scene actual use speech recognition technology
Following problem is found in the process:
Sound equipment or power amplifying device sound in court is bigger, there is many branch microphones in a court.If court's trial
The sound of sound equipment or power amplifier feedback can be picked up if the microphone directive property at scene is poor, so as to cause speech recognition system
Identify the unwanted text of some reality.In addition, in court, the microphone of defendant and defender from close, Yuan Gaohe
The microphone of defender from it is close, the microphone of judge and judge from also close, the Mike not talked practical in this way
Wind may pick up the sound of adjacent teller, identify the unwanted text of some reality so as to cause speech recognition system
Word.
Summary of the invention
The embodiment of the present invention provides a kind of method for eliminating court's trial noise jamming, dry to eliminate the noise in court trial process
It disturbs, speech recognition system is avoided to identify the unwanted text of some reality, this method comprises:
The sound of court's trial scene multichannel microphone is acquired, wherein having a noise threshold per microphone preset all the way;
The volume of multichannel microphone is compared with corresponding noise threshold, if the volume of microphone is higher than corresponding
The sound of the microphone is then sent to speech recognition system by noise threshold, if the volume of microphone is lower than corresponding noise
Threshold values then carries out silence processing to the microphone.
Optionally, this method further include:
The multichannel microphone at court's trial scene is grouped, the distance between every group multiple microphones are in setting range
It is interior;
Identical noise threshold is arranged to each group of microphone.
Optionally, if the volume of microphone is higher than corresponding noise threshold, the sound of the microphone is sent to language
Sound identifying system carries out silence processing to the microphone if the volume of microphone is lower than corresponding noise threshold, comprising:
If only having the volume of microphone to be all the way higher than the noise threshold of this group of microphone in one group, by the microphone
Sound is sent to speech recognition system;
If there is the volume of multichannel microphone to be higher than the noise threshold of this group of microphone in one group, this group of Mike will be above
The multichannel microphone of wind noise threshold values sorts according to volume;
Sequence is greater than the microphone progress silence processing that this group of microphone preset opens number;
The sound that sequence is less than or equal to the microphone that this group of microphone preset opens number is sent to speech recognition system.
Optionally, if the noise threshold for thering is the volume of multichannel microphone to be higher than this group of microphone in one group, to this
Before the multichannel microphone of group carries out volume sequence, enhance the volume of the microphone of highest priority in the group.
The embodiment of the present invention also provides a kind of device for eliminating court's trial noise jamming, to eliminate the noise in court trial process
Interference, avoids speech recognition system from identifying that the unwanted text of some reality, the device include:
Sound acquisition module, for acquiring the sound of court's trial scene multichannel microphone, wherein having per microphone preset all the way
One noise threshold;
Noise processed module, for the volume of multichannel microphone to be compared with corresponding noise threshold, if Mike
The volume of wind is higher than corresponding noise threshold, then the sound of the microphone is sent to speech recognition system, if microphone
Volume is lower than corresponding noise threshold, then carries out silence processing to the microphone.
Optionally, the device further include:
Optimization module is grouped for the multichannel microphone to court's trial scene, between every group of multiple microphones away from
From within the set range;
Identical noise threshold is arranged to each group of microphone.
Optionally, in noise processed module, if only the volume of microphone is higher than this group of microphone all the way in one group
Noise threshold, then the sound of the microphone is sent to speech recognition system;
If there is the volume of multichannel microphone to be higher than the noise threshold of this group of microphone in one group, this group of Mike will be above
The multichannel microphone of wind noise threshold values sorts according to volume;
Sequence is greater than the microphone progress silence processing that this group of microphone preset opens number;
The sound that sequence is less than or equal to the microphone that this group of microphone preset opens number is sent to speech recognition system.
Optionally, in noise processed module, if there is the volume of multichannel microphone to be higher than this group of microphone in one group
Noise threshold enhances the Mike of highest priority in the group then before the multichannel microphone to the group carries out volume sequence
The volume of wind.
The embodiment of the present invention also provides a kind of computer equipment, including memory, processor and storage are on a memory simultaneously
The computer program that can be run on a processor, the processor realize the above method when executing the computer program.
The embodiment of the present invention also provides a kind of computer readable storage medium, and the computer-readable recording medium storage has
Execute the computer program of the above method.
The method provided in an embodiment of the present invention for eliminating court's trial noise jamming passes through acquisition court's trial scene multichannel microphone
Sound lays a good foundation to the noise threshold per microphone preset one all the way for subsequent elimination noise jamming.By by multichannel
The volume of microphone is compared with corresponding noise threshold, will if the volume of microphone is higher than corresponding noise threshold
The sound of the microphone is sent to speech recognition system, if the volume of microphone is lower than corresponding noise threshold, to the wheat
Gram wind carries out silence processing, preferably protects primary sound, and noise is only carried out silence processing, i.e., is fed back to sound equipment or power amplifier
Sound and the sound of adjacent teller carry out silence processing, eliminate the noise jamming in court trial process, avoid speech recognition
System identification goes out the unwanted text of some reality.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.In the accompanying drawings:
Fig. 1 is the flow diagram that the method for court's trial noise jamming is eliminated in the embodiment of the present invention;
Fig. 2 is the structural schematic diagram that the device of court's trial noise jamming is eliminated in the embodiment of the present invention;
Fig. 3 is the packet transaction exemplary diagram of microphone in the embodiment of the present invention;
Fig. 4 is the specific example figure that the method for court's trial noise jamming is eliminated in the embodiment of the present invention.
Specific embodiment
Understand in order to make the object, technical scheme and advantages of the embodiment of the invention clearer, with reference to the accompanying drawing to this hair
Bright embodiment is described in further details.Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but simultaneously
It is not as a limitation of the invention.
When law court tries case, clerk is needed to record the speech content of each role.With artificial intelligence
Development, speech recognition technology is more and more mature, and speech recognition system can accomplish very high correct recognition rata, complete to it
After face is promoted, the workload of clerk can be greatly reduced.But at present in court's trial scene actual use speech recognition technology
Following problem is found in the process:
Sound equipment or power amplifying device sound in court is bigger, there is many branch microphones in a court.If court's trial
The sound of sound equipment or power amplifier feedback can be picked up if the microphone directive property at scene is poor, so as to cause speech recognition system
Identify the unwanted text of some reality.In addition, in court, the microphone of defendant and defender from close, Yuan Gaohe
The microphone of defender from it is close, the microphone of judge and judge from also close, the Mike not talked practical in this way
Wind may pick up the sound of adjacent teller, identify the unwanted text of some reality so as to cause speech recognition system
Word.To solve the above-mentioned problems, the embodiment of the invention provides a kind of methods for eliminating court's trial noise jamming, as shown in Fig. 1,
This method comprises:
Step 101, the sound for acquiring court's trial scene multichannel microphone, wherein having a noise valve per microphone preset all the way
Value;
The volume of multichannel microphone is compared by step 102 with corresponding noise threshold, if the volume of microphone is high
In corresponding noise threshold, then the sound of the microphone is sent to speech recognition system, if the volume of microphone lower than pair
The noise threshold answered then carries out silence processing to the microphone.
The method provided in an embodiment of the present invention for eliminating court's trial noise jamming passes through acquisition court's trial scene multichannel microphone
Sound lays a good foundation to the noise threshold per microphone preset one all the way for subsequent elimination noise jamming.By by multichannel
The volume of microphone is compared with corresponding noise threshold, will if the volume of microphone is higher than corresponding noise threshold
The sound of the microphone is sent to speech recognition system, if the volume of microphone is lower than corresponding noise threshold, to the wheat
Gram wind carries out silence processing, preferably protects primary sound, and noise is only carried out silence processing, i.e., is fed back to sound equipment or power amplifier
Sound and the sound of adjacent teller carry out silence processing, eliminate the noise jamming in court trial process, avoid speech recognition
System identification goes out the unwanted text of some reality.
In order to which the noise to adjacent teller is further screened, it is ensured that noise jamming can be accurately and efficiently excluded,
This method further include:
The multichannel microphone at court's trial scene is grouped, the distance between every group multiple microphones are in setting range
It is interior;
Identical noise threshold is arranged to each group of microphone.Specifically grouping example can be found in attached drawing 3.
Wherein, " the distance between every group multiple microphones are within the set range " refers to: every group of multiple microphones
The distance between it is close, for example, the microphone of defendant and its defender can be one group, the Mike of plaintiff and its defender
Wind can be one group, and the microphone of judge and judge can be one group.
Further, since every group there are multiple microphones, and in order to exclude noise jamming, wherein some Mike is only released
The sound of wind carries out silence processing to other microphones.If the volume of microphone is higher than corresponding noise threshold, by the wheat
The sound of gram wind is sent to speech recognition system, if the volume of microphone is lower than corresponding noise threshold, to the microphone
Carry out silence processing, comprising:
If only having the volume of microphone to be all the way higher than the noise threshold of this group of microphone in one group, by the microphone
Sound is sent to speech recognition system;
If there is the volume of multichannel microphone to be higher than the noise threshold of this group of microphone in one group, this group of Mike will be above
The multichannel microphone of wind noise threshold values sorts according to volume;
Sequence is greater than the microphone progress silence processing that this group of microphone preset opens number;
The sound that sequence is less than or equal to the microphone that this group of microphone preset opens number is sent to speech recognition system.
Specifically, for example, if one group shares three microphones, and the volume of this three microphones is all higher than the group
The noise threshold of microphone, but the default opening number of the group only has two, then according to the ranking results of volume, will sort
The sound for the microphone that less than or equal to this group microphone preset opens number is sent to speech recognition system.
Further, since the priority of court's trial scene role is different, microphone priority used in different role
Grade is also different, in order to protrude the sound of highest priority, before the multichannel microphone to the group carries out volume sequence,
Enhance the volume of the microphone of highest priority in the group.
Based on the same inventive concept, a kind of voice-activated dress applied to digital court is additionally provided in the embodiment of the present invention
It sets, as described in the following examples.Due to being applied to the principle that solves the problems, such as of voice-activated device of digital court and being applied to
The voice-activated method of digital court is similar, and therefore, the implementation of the voice-activated device applied to digital court may refer to answer
The implementation of voice-activated method for digital court, overlaps will not be repeated.It is used below, term " unit " or
The combination of the software and/or hardware of predetermined function may be implemented in " module ".Although device is preferably described in following embodiment
It is realized with software, but the realization of the combination of hardware or software and hardware is also that may and be contemplated.
The embodiment of the invention also provides a kind of devices for eliminating court's trial noise jamming, as shown in Fig. 2, this method packet
It includes:
Sound acquisition module 201, for acquiring the sound of court's trial scene multichannel microphone, wherein per microphone preset all the way
There is a noise threshold;
Noise processed module 202, for the volume of multichannel microphone to be compared with corresponding noise threshold, if wheat
The volume of gram wind is higher than corresponding noise threshold, then the sound of the microphone is sent to speech recognition system, if microphone
Volume be lower than corresponding noise threshold, then to the microphone carry out silence processing.
In embodiments of the present invention, the device further include:
Optimization processing module 203 is grouped for the multichannel microphone to court's trial scene, every group of multiple microphones it
Between distance within the set range;
Identical noise threshold is arranged to each group of microphone.
In embodiments of the present invention, in noise processed module 202, if only the volume of microphone is high all the way in one group
In the noise threshold of this group of microphone, then the sound of the microphone is sent to speech recognition system;
If there is the volume of multichannel microphone to be higher than the noise threshold of this group of microphone in one group, this group of Mike will be above
The multichannel microphone of wind noise threshold values sorts according to volume;
Sequence is greater than the microphone progress silence processing that this group of microphone preset opens number;
The sound that sequence is less than or equal to the microphone that this group of microphone preset opens number is sent to speech recognition system.
In embodiments of the present invention, in noise processed module 202, if there is the volume of multichannel microphone to be higher than in one group
The noise threshold of this group of microphone enhances preferential in the group then before the multichannel microphone to the group carries out volume sequence
The volume of the highest microphone of grade.
The embodiment of the invention also provides a kind of computer readable storage medium, computer-readable recording medium storage is held
The computer program of the row above method.
As shown in Fig. 4, below by taking microphone all the way as an example, process flow of the invention is illustrated, it is specifically, right
The method for processing noise of microphone is as follows all the way:
Acquire the sound of this road microphone.
The volume for calculating this road microphone is used herein as the common volume algorithm in this field.
For one volume threshold of each microphone preset, which be may be the same or different, if general multichannel
Microphone with the positional distance of sound equipment or power amplifier it is close when threshold value be both configured to it is identical.
By the volume of this road microphone, with its, corresponding threshold value is compared, and what is used herein is that this field carries out threshold values meter
The common threshold restriction algorithm calculated.
If the volume of this road microphone is lower than its corresponding threshold value, the practical nobody's speech of this microphone is proved,
The sound of acquisition may be the sound of sound equipment or power amplifier, or talk apart from the closer people of this microphone, so needing
It is quiet data to the processing of this kind of audio data, used herein is muting algorithm.If the volume of this road microphone is higher than it
Corresponding threshold value is then grouped processing to audio data.
Have several important parameters during packet transaction, such as priority and priority step value, the two parameters with
It is related to calculate secondary sound volume value.The effect that priority and priority step value is arranged is some roles in practical court trial process
Speech will be prior to other roles.
Secondary sound volume computational algorithm, substantially realization principle are that secondary sound volume value is equal to multiplying for priority and priority step value
Product is plus the volume value calculated for the first time;
Secondary sound volume value is compared with the threshold value of PHM packet handling module, threshold restriction algorithm used herein;
If secondary sound volume value is lower than threshold value, speech recognition system is given after the processing of audio data muting algorithm.If two
Secondary volume value is higher than threshold value, then compares with same group other road microphones, obtains the ranking of original microphone in a packet, this
Place uses sort algorithm commonly used in the art;
The opening microphone number for judging whether the ranking of this road microphone is less than or equal in same group (opens microphone number just
Referring to can have several microphones more than threshold value sound can be given speech recognition system simultaneously in a PHM packet handling module
System), if it is less than or equal to open microphone number, then prove that this road microphone is the microphone actually talked in this grouping,
Directly this road, audio data is given to speech recognition system, on the contrary, the audio data of the road Ze Duizhe microphone carries out muting algorithm
Speech recognition system, muting algorithm used herein are resent to after processing.
To sum up, the method provided in an embodiment of the present invention for eliminating court's trial noise jamming, by acquiring court's trial scene multichannel wheat
The sound of gram wind lays a good foundation to the noise threshold per microphone preset one all the way for subsequent elimination noise jamming.Pass through
The volume of multichannel microphone is compared with corresponding noise threshold, if the volume of microphone is higher than corresponding noise valve
Value, then be sent to speech recognition system for the sound of the microphone, if the volume of microphone is lower than corresponding noise threshold,
Silence processing is carried out to the microphone, preferably protects primary sound, noise is only subjected to silence processing, i.e., to sound equipment or power amplifier
The sound of feedback and the sound of adjacent teller carry out silence processing, eliminate the noise jamming in court trial process, avoid language
Sound identifying system identifies the unwanted text of some reality.
In embodiment, since every group has multiple microphones, and in order to exclude noise jamming, the present invention can only release it
In some microphone sound, to other microphones carry out silence processing.And in order to protrude the spokesman of highest priority
The microphone used can enhance the volume of the microphone when the spokesman makes a speech, so as to audience can listen it is clearer.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
Describe in detail it is bright, it should be understood that the above is only a specific embodiment of the present invention, the guarantor being not intended to limit the present invention
Range is protected, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should be included in this
Within the protection scope of invention.
Claims (10)
1. a kind of method for eliminating court's trial noise jamming characterized by comprising
The sound of court's trial scene multichannel microphone is acquired, wherein having a noise threshold per microphone preset all the way;
The volume of multichannel microphone is compared with corresponding noise threshold, if the volume of microphone is higher than corresponding noise
The sound of the microphone is then sent to speech recognition system by threshold values, if the volume of microphone is lower than corresponding noise threshold,
Silence processing then is carried out to the microphone.
2. the method as described in claim 1, which is characterized in that further include:
The multichannel microphone at court's trial scene is grouped, the distance between every group multiple microphones are within the set range;
Identical noise threshold is arranged to each group of microphone.
3. method according to claim 2, which is characterized in that if the volume of microphone is higher than corresponding noise threshold,
The sound of the microphone is sent to speech recognition system, if the volume of microphone is lower than corresponding noise threshold, to this
Microphone carries out silence processing, comprising:
If only having the volume of microphone to be all the way higher than the noise threshold of this group of microphone in one group, by the sound of the microphone
It is sent to speech recognition system;
If there is the volume of multichannel microphone to be higher than the noise threshold of this group of microphone in one group, it will be above this group of microphone and make an uproar
The multichannel microphone of sound threshold values sorts according to volume;
Sequence is greater than the microphone progress silence processing that this group of microphone preset opens number;
The sound that sequence is less than or equal to the microphone that this group of microphone preset opens number is sent to speech recognition system.
4. method as claimed in claim 3, which is characterized in that if there is the volume of multichannel microphone to be higher than this group of wheat in one group
The noise threshold of gram wind enhances highest priority in the group then before the multichannel microphone to the group carries out volume sequence
Microphone volume.
5. a kind of device for eliminating court's trial noise jamming characterized by comprising
Sound acquisition module, for acquiring the sound of court's trial scene multichannel microphone, wherein having one per microphone preset all the way
Noise threshold;
Noise processed module, for the volume of multichannel microphone to be compared with corresponding noise threshold, if microphone
Volume is higher than corresponding noise threshold, then the sound of the microphone is sent to speech recognition system, if the volume of microphone
Lower than corresponding noise threshold, then silence processing is carried out to the microphone.
6. device as claimed in claim 5, which is characterized in that further include:
Optimization module is grouped for the multichannel microphone to court's trial scene, and the distance between every group multiple microphones exist
In setting range;
Identical noise threshold is arranged to each group of microphone.
7. device as claimed in claim 6, which is characterized in that in noise processed module, if there was only wheat all the way in one group
The volume of gram wind is higher than the noise threshold of this group of microphone, then the sound of the microphone is sent to speech recognition system;
If there is the volume of multichannel microphone to be higher than the noise threshold of this group of microphone in one group, it will be above this group of microphone and make an uproar
The multichannel microphone of sound threshold values sorts according to volume;
Sequence is greater than the microphone progress silence processing that this group of microphone preset opens number;
The sound that sequence is less than or equal to the microphone that this group of microphone preset opens number is sent to speech recognition system.
8. device as claimed in claim 7, which is characterized in that in noise processed module, if there is multichannel Mike in one group
The volume of wind is higher than the noise threshold of this group of microphone, then before the multichannel microphone to the group carries out volume sequence, increases
The volume of the microphone of highest priority in the strong group.
9. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes any side of Claims 1-4 when executing the computer program
Method.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has perform claim
It is required that the computer program of 1 to 4 any the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910140271.XA CN109785864B (en) | 2019-02-26 | 2019-02-26 | Method and device for eliminating court trial noise interference |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910140271.XA CN109785864B (en) | 2019-02-26 | 2019-02-26 | Method and device for eliminating court trial noise interference |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109785864A true CN109785864A (en) | 2019-05-21 |
CN109785864B CN109785864B (en) | 2021-02-05 |
Family
ID=66487203
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910140271.XA Active CN109785864B (en) | 2019-02-26 | 2019-02-26 | Method and device for eliminating court trial noise interference |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109785864B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115881131A (en) * | 2022-11-17 | 2023-03-31 | 广州市保伦电子有限公司 | Voice transcription method under multiple voices |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201967133U (en) * | 2011-01-27 | 2011-09-07 | 北京华夏电通科技有限公司 | Host used for multi-channel speech mixing and camera tracking |
CN103379231A (en) * | 2012-04-17 | 2013-10-30 | 中兴通讯股份有限公司 | Wireless conference phone and method for wireless conference phone performing voice signal transmission |
US20140247319A1 (en) * | 2013-03-01 | 2014-09-04 | Citrix Systems, Inc. | Controlling an electronic conference based on detection of intended versus unintended sound |
JP2015069063A (en) * | 2013-09-30 | 2015-04-13 | 日本電気通信システム株式会社 | Voice recognition system, voice recognition method, and voice recognition program |
CN105657329A (en) * | 2016-02-26 | 2016-06-08 | 苏州科达科技股份有限公司 | Video conference system, processing device and video conference method |
CN108449687A (en) * | 2018-03-13 | 2018-08-24 | 江苏华腾智能科技有限公司 | A kind of conference system of multi-microphone array noise reduction |
-
2019
- 2019-02-26 CN CN201910140271.XA patent/CN109785864B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201967133U (en) * | 2011-01-27 | 2011-09-07 | 北京华夏电通科技有限公司 | Host used for multi-channel speech mixing and camera tracking |
CN103379231A (en) * | 2012-04-17 | 2013-10-30 | 中兴通讯股份有限公司 | Wireless conference phone and method for wireless conference phone performing voice signal transmission |
US20140247319A1 (en) * | 2013-03-01 | 2014-09-04 | Citrix Systems, Inc. | Controlling an electronic conference based on detection of intended versus unintended sound |
CN105144628A (en) * | 2013-03-01 | 2015-12-09 | 思杰系统有限公司 | Controlling an electronic conference based on detection of intended versus unintended sound |
JP2015069063A (en) * | 2013-09-30 | 2015-04-13 | 日本電気通信システム株式会社 | Voice recognition system, voice recognition method, and voice recognition program |
CN105657329A (en) * | 2016-02-26 | 2016-06-08 | 苏州科达科技股份有限公司 | Video conference system, processing device and video conference method |
CN108449687A (en) * | 2018-03-13 | 2018-08-24 | 江苏华腾智能科技有限公司 | A kind of conference system of multi-microphone array noise reduction |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115881131A (en) * | 2022-11-17 | 2023-03-31 | 广州市保伦电子有限公司 | Voice transcription method under multiple voices |
CN115881131B (en) * | 2022-11-17 | 2023-10-13 | 广东保伦电子股份有限公司 | Voice transcription method under multiple voices |
Also Published As
Publication number | Publication date |
---|---|
CN109785864B (en) | 2021-02-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108630193B (en) | Voice recognition method and device | |
CN102388416B (en) | Signal processing apparatus and signal processing method | |
US9412371B2 (en) | Visualization interface of continuous waveform multi-speaker identification | |
CN109389989B (en) | Sound mixing method, device, equipment and storage medium | |
CN111800723B (en) | Active noise reduction earphone testing method and device, terminal equipment and storage medium | |
CN110956976B (en) | Echo cancellation method, device and equipment and readable storage medium | |
Kinoshita et al. | Tackling real noisy reverberant meetings with all-neural source separation, counting, and diarization system | |
CN110136696B (en) | Audio data monitoring processing method and system | |
JP4462617B2 (en) | Sound source separation device, sound source separation program, and sound source separation method | |
US20130246061A1 (en) | Automatic realtime speech impairment correction | |
CN109961797A (en) | A kind of echo cancel method, device and electronic equipment | |
WO2022134351A1 (en) | Noise reduction method and system for monophonic speech, and device and readable storage medium | |
CN110364178A (en) | Voice processing method and device, storage medium and electronic equipment | |
CN110428835A (en) | A kind of adjusting method of speech ciphering equipment, device, storage medium and speech ciphering equipment | |
CN109785864A (en) | Eliminate the method and device of court's trial noise jamming | |
Lebourdais et al. | Joint speech and overlap detection: a benchmark over multiple audio setup and speech domains | |
CN111968620B (en) | Algorithm testing method and device, electronic equipment and storage medium | |
CN110544472B (en) | Method for improving performance of voice task using CNN network structure | |
US10771913B2 (en) | Determining sound locations in multi-channel audio | |
CN111696573A (en) | Sound source signal processing method and device, electronic equipment and storage medium | |
US11863946B2 (en) | Method, apparatus and computer program for processing audio signals | |
US11682414B1 (en) | Adjusting audio transparency based on content | |
CN109841223A (en) | A kind of acoustic signal processing method, intelligent terminal and storage medium | |
US8462984B2 (en) | Data pattern recognition and separation engine | |
CN110992966B (en) | Human voice separation method and system |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 100094 5 floor 101, 6 building, No. 3, Fung Xiu Road, Haidian District, Beijing. Applicant after: BEIJING HUAXIA DENTSU TECHNOLOGY Co.,Ltd. Address before: 100094 5 floor 101, 6 building, No. 3, Fung Xiu Road, Haidian District, Beijing. Applicant before: BEIJING CHINASYS TECHNOLOGIES Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |