CN110348011A - A kind of with no paper meeting shows that object determines method, apparatus and storage medium - Google Patents

A kind of with no paper meeting shows that object determines method, apparatus and storage medium Download PDF

Info

Publication number
CN110348011A
CN110348011A CN201910556845.1A CN201910556845A CN110348011A CN 110348011 A CN110348011 A CN 110348011A CN 201910556845 A CN201910556845 A CN 201910556845A CN 110348011 A CN110348011 A CN 110348011A
Authority
CN
China
Prior art keywords
meeting
voice signal
shows
paper
calibration
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
Application number
CN201910556845.1A
Other languages
Chinese (zh)
Inventor
杜子科
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Guanke Intelligent Technology Co Ltd
Original Assignee
Wuhan Guanke Intelligent Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan Guanke Intelligent Technology Co Ltd filed Critical Wuhan Guanke Intelligent Technology Co Ltd
Priority to CN201910556845.1A priority Critical patent/CN110348011A/en
Publication of CN110348011A publication Critical patent/CN110348011A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16Sound input; Sound output
    • G06F3/165Management of the audio stream, e.g. setting of volume, audio stream path
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/30Semantic analysis
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/26Speech to text systems
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/02Details
    • H04L12/16Arrangements for providing special services to substations
    • H04L12/18Arrangements for providing special services to substations for broadcast or conference, e.g. multicast
    • H04L12/1813Arrangements for providing special services to substations for broadcast or conference, e.g. multicast for computer conferences, e.g. chat rooms
    • H04L12/1822Conducting the conference, e.g. admission, detection, selection or grouping of participants, correlating users to one or more conference sessions, prioritising transmission

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Acoustics & Sound (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

The present invention relates to a kind of with no paper meetings to show that object determines method, apparatus and storage medium.This method comprises the following steps: obtaining the voice signal that calibration shows object by microphone;It determines the decibel information of the voice signal, and speech recognition is carried out to the voice signal, extract and obtain semantic information;The decibel information and institute's semantic information are compared with preset condition, determined whether the calibration showing that the voice signal of object accesses meeting-place lines of loudspeakers according to comparison result.Technical solution of the present invention can improve the communication efficiency and communicative effect of with no paper meeting.

Description

A kind of with no paper meeting shows that object determines method, apparatus and storage medium
Technical field
The present invention relates to no paper conferencing technology fields, and in particular to a kind of with no paper meeting show object determine method, Device and storage medium.
Background technique
When carrying out with no paper meeting, it usually needs the equipment such as microphone, loudspeaker, video camera and display give auxiliary It helps, to complete to show meeting object, that is, carries out the acquisition of the information such as voice and image to such as current speaker, and in Meeting-place is shown.But by taking speech utterance as an example, at present when certain personnel participating in the meeting wishes speech, it usually needs mention first Speaking request is played, then starts the microphone of the personnel participating in the meeting by background work personnel, if background work personnel do not locate in time Reason, meeting probably because can not effectively, sufficiently link up due to go on smoothly, this will affect the communication efficiency and friendship of with no paper meeting Flow effect.
Summary of the invention
In view of the deficiencies of the prior art, the present invention provides a kind of with no paper meeting and shows that object determines method, apparatus and deposits Storage media.
In a first aspect, the present invention provides a kind of with no paper meetings to show that object determines that method, this method include following step It is rapid:
The voice signal that calibration shows object is obtained by microphone.
It determines the decibel information of the voice signal, and speech recognition is carried out to the voice signal, extract and obtain semanteme Information.
The decibel information and institute's semantic information are compared with preset condition, according to comparison result determine whether by The calibration shows that the voice signal of object accesses meeting-place lines of loudspeakers.
Second aspect, the present invention provides a kind of with no paper meetings to show object determining device, which includes:
Module is obtained, for obtaining the voice signal that calibration shows object by microphone.
Identification module carries out speech recognition for determining the decibel information of the voice signal, and to the voice signal, It extracts and obtains semantic information.
Processing module, for the decibel information and institute's semantic information to be compared with preset condition, according to comparing As a result determine whether the calibration showing that the voice signal of object accesses meeting-place lines of loudspeakers.
The third aspect, the present invention provides a kind of with no paper meetings to show object determining device, which includes memory And processor;The memory, for storing computer program;The processor is used for when loaded and executed, Realize that with no paper meeting as described above shows that object determines method.
Fourth aspect is stored with computer on the storage medium the present invention provides a kind of computer readable storage medium Program realizes that with no paper meeting as described above shows that object determines method when the computer program is executed by processor.
With no paper meeting displaying object provided by the invention determines that the beneficial effect of method, apparatus and storage medium is, When carrying out such as with no paper roundtable conference, usual every participant, that is, can be carried out before the displaying object surface of speech It can be equipped with a microphone, the voice signal of participant is mainly acquired by microphone in front.Carrying out more person-times of speech exhibitions When showing, each microphone collects the voice signal of its corresponding participant.Voice signal has certain decibel value, and After carrying out intelligent sound identification to it, corresponding semantic information can be obtained, that is, converts voice signals into corresponding text Signal.Should have by the analysis to decibel information and semantic information, such as when decibel value reaches preset normal speech Decibel value or semantic information in include indicate the participant need really normally participate in conference speech vocabulary when, can The voice signal of the participant is directly accessed into the meeting-place loudspeaker in no paper conference system based on real-time analysis result, is made Other participants, which can understand, to be heard.Since to qualified displaying object, voice signal can be directly by loudspeaker It plays, avoids the need for sending speaking request to backstage personnel first, then give the redundancy link of competence of speech by backstage personnel. Show that object by the way that automatic, accurately acquisition shows permission, can improve the communication efficiency and communicative effect of with no paper meeting.
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 this hair Bright some embodiments for those of ordinary skill in the art without any creative labor, can be with It obtains other drawings based on these drawings.
Fig. 1 is that the with no paper meeting of the embodiment of the present invention shows that object determines the flow diagram of method;
Fig. 2 is that the with no paper meeting of the embodiment of the present invention shows the structural block diagram of object determining device.
Specific embodiment
The principle and features of the present invention will be described below with reference to the accompanying drawings, and the given examples are served only to explain the present invention, and It is non-to be used to limit the scope of the invention.
As shown in Figure 1, a kind of with no paper meeting of the embodiment of the present invention shows that object determines that method includes the following steps:
S1, the voice signal that calibration shows object is obtained by microphone.
S2, the decibel information for determining the voice signal, and speech recognition is carried out to the voice signal, it extracts and obtains language Adopted information.
S3, the decibel information and institute's semantic information are compared with preset condition, are according to comparison result determination It is no that the calibration is shown that the voice signal of object accesses meeting-place lines of loudspeakers.
In the present embodiment, when carrying out such as with no paper roundtable conference, usual every participant, that is, may be into It can be equipped with a microphone before the displaying object surface of row speech, the voice signal of participant is mainly by Mike's elegance in front Collection.When carrying out more person-times of speeches displayings, each microphone collects the voice signal of its corresponding participant.Sound letter Number there is certain decibel value, and after carrying out intelligent sound identification to it, can obtain corresponding semantic information, that is, by voice Signal is converted to corresponding letter signal.By the analysis to decibel information and semantic information, such as when decibel value reaches default Normally the make a speech decibel value that have or semantic information in include indicate the participant need normally to participate in really When the vocabulary of conference speech, the voice signal of the participant directly can be accessed into no paper meeting system based on real-time analysis result Meeting-place loudspeaker in system understand other participants can and hear.Due to qualified displaying object, sound letter It number can directly be played by loudspeaker, avoid the need for sending speaking request to backstage personnel first, then given by backstage personnel The redundancy link of competence of speech.Show that object by the way that automatic, accurately acquisition shows permission, can improve the ditch of with no paper meeting Logical efficiency and communicative effect.
Preferably, the preset condition includes:
When the decibel information is more than preset threshold, and/or, it include matched with institute semantic information in presetting database When at least one access keyword, the calibration is shown that the voice signal of object accesses meeting-place lines of loudspeakers.
Specifically, since the volume normally made a speech can be more than certain decibel numerical value, calibration can be shown into object Whether the decibel value of voice signal is more than preset threshold as one of condition.Meanwhile it can also be by voice messaging and presetting database In access keyword compare, comparing result also can be used as one of condition.For example, detecting that calibration shows the sound of object The decibel value of signal reaches 60, has been more than preset threshold 50, and identifies that from its voice signal, the semantic information of extraction includes When " asking ", " thanks " and " ecological protection " etc. is with three of the access Keywords matching in presetting database and the above vocabulary, card Its bright speech content and meeting are closely related, its voice signal can be automatically accessed to meeting-place loudspeaker and played out, reduction need not That wants waits until the time, understands other participants and hears, improves conference content communication efficiency.
Preferably, the preset condition further include:
After the calibration shows the voice signal access meeting-place lines of loudspeakers of object, when the decibel information is low In the preset threshold and when the decibel information is more than preset duration lower than the duration of the preset threshold, by the mark Surely show that the voice signal of object cuts out meeting-place lines of loudspeakers.
Specifically, it after the completion of calibration shows object speech, may no longer make a speech, if detected from the displaying pair The decibel value of the voice signal of elephant is lower than preset threshold, and continues for some time, for example, 60 seconds after participant speech Interior, the decibel value of the voice signal of corresponding microphone acquisition is below 50, illustrates that it may not be needed to continue to participate in this wheel speech, Its voice signal, can be cut out meeting-place speaker wire by the influence in order to avoid the noise from this to other participants simultaneously Road.It also needs to make a speech if its is subsequent, speech recognition and analysis result line attachment can be passed through again.
Preferably, the preset condition further include:
After the calibration shows the voice signal access meeting-place lines of loudspeakers of object, when from the voice signal It is pre-stored in the presetting database in institute's semantic information that middle extract real-time obtains including at least one and forbids keyword When, the calibration is shown that the voice signal of object cuts out meeting-place lines of loudspeakers.
Specifically, during calibration shows object speech, if finding that its speech includes with analysis through speech recognition In presetting database when forbidding keyword, such as occur uncivil term or country prohibite theme relative words when, In order to avoid its speech is propagated in all participants, the voice signal of the displaying object can directly be cut out meeting-place loudspeaker Route.It also needs to make a speech if its is subsequent, carries out manual examination and verification to it first, then pass through speech recognition and analysis result tie-in line Road.
Preferably, the access keyword include in respect language, preset session topic word and preset key vocabulary extremely Few one.
Specifically, respect language includes " asking ", " thanks " and " being honored " etc., and session topic word includes relevant to this meeting Keyword, such as " environmental protection ", " big data " etc., can be arranged in advance, key vocabulary can be sponsored by meeting by meeting sponsor Side's setting, and may be notified that participant, similar connector password.If including above-mentioned in the semantic information through speech recognition and analysis Vocabulary then illustrates that the speech content of the spokesman is really related to meeting, needs to access loudspeaker and play out.Improve meeting The efficiency that content is linked up.
Preferably, the method also includes following steps:
Control meeting-place video camera shooting picture signal corresponding with the calibration displaying object that the voice signal indicates, And described image signal is accessed into meeting field display route.
Specifically, for for example needing the case where showing hand-held article etc., current speaker is not only played by loudspeaker Voice signal, its display image signal is also played by display, conference content is made to show more abundant, improve meeting ditch Logical effect.Meanwhile also the spokesman can be reminded by the picture signal of display, voice signal has accessed lines of loudspeakers.
Preferably, the method also includes following steps:
When there are the corresponding different multiway images signal access meeting field display routes for showing object, believed according to described image Number quantity will the screen of field display be divided into multiple regions, and multichannel described image signal is projected to respectively corresponding The region.
Specifically, for for example being argued or the meeting situation made a speech in turn, in the sound for playing different spokesmans respectively While sound signal, its corresponding picture signal can be also illustrated on display respectively, further sufficiently show that meeting has Content is imitated, meeting communication effectiveness is improved.
As shown in Fig. 2, the with no paper meeting of the embodiment of the present invention shows that object determining device includes:
Module is obtained, for obtaining the voice signal that calibration shows object by microphone.
Identification module carries out speech recognition for determining the decibel information of the voice signal, and to the voice signal, It extracts and obtains semantic information.
Processing module, for the decibel information and institute's semantic information to be compared with preset condition, according to comparing As a result determine whether the calibration showing that the voice signal of object accesses meeting-place lines of loudspeakers.
Preferably, the processing module is specifically used for: when the decibel information be more than preset threshold, and/or, preset data When including at least one access keyword matched with institute semantic information in library, the calibration is shown to the sound of object Signal accesses meeting-place lines of loudspeakers.
Preferably, the processing module is specifically also used to: showing that the voice signal of object accesses meeting in the calibration After the lines of loudspeakers of field, when the decibel information is lower than the preset threshold and the decibel information is lower than the preset threshold When duration is more than preset duration, the calibration is shown that the voice signal of object cuts out meeting-place lines of loudspeakers.
Preferably, the processing module is specifically also used to: showing that the voice signal of object accesses meeting in the calibration After lines of loudspeakers, when being prestored in the institute's semantic information obtained from extract real-time in the voice signal including at least one In the presetting database when forbidding keyword, by it is described calibration show object the voice signal cut out meeting-place loudspeaking Device route.
Preferably, the access keyword include in respect language, preset session topic word and preset key vocabulary extremely Few one.
Preferably, the processing module is specifically also used to: the shooting of control meeting-place video camera and voice signal instruction The calibration shows the corresponding picture signal of object, and described image signal is accessed can field display route.
Preferably, the processing module is specifically used for: when the multiway images signal access meeting for having corresponding different displaying objects When field display route, according to the quantity of described image signal will the screen of field display be divided into multiple regions, and respectively Multichannel described image signal is projected to the corresponding region.
In an alternative embodiment of the invention, a kind of with no paper meeting shows that object determining device includes memory and processing Device.The memory, for storing computer program.The processor, for when loaded and executed, realizing such as The upper with no paper meeting shows that object determines method.The device can be the computer installations such as server.
In an alternative embodiment of the invention, it is stored with computer program on a kind of computer readable storage medium, when described When computer program is executed by processor, realize that with no paper meeting as described above shows that object determines method.
Reader should be understood that in the description of this specification reference term " one embodiment ", " is shown " some embodiments " The description of example ", specific examples or " some examples " etc. mean specific features described in conjunction with this embodiment or example, structure, Material or feature are included at least one embodiment or example of the invention.In the present specification, above-mentioned term is shown The statement of meaning property need not be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples Sign is combined.
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example Property, it is not considered as limiting the invention, those skilled in the art within the scope of the invention can be to above-mentioned Embodiment is changed, modifies, replacement and variant.

Claims (10)

1. a kind of with no paper meeting shows that object determines method, which is characterized in that described method includes following steps:
The voice signal that calibration shows object is obtained by microphone;
It determines the decibel information of the voice signal, and speech recognition is carried out to the voice signal, extract and obtain semantic information;
The decibel information and institute's semantic information are compared with preset condition, being determined whether according to comparison result will be described Calibration shows that the voice signal of object accesses meeting-place lines of loudspeakers.
2. with no paper meeting according to claim 1 shows that object determines method, which is characterized in that the preset condition packet It includes:
When the decibel information is more than preset threshold, and/or, it include matched at least with institute semantic information in presetting database When one access keyword, the calibration is shown that the voice signal of object accesses meeting-place lines of loudspeakers.
3. with no paper meeting according to claim 2 shows that object determines method, which is characterized in that the preset condition is also Include:
After the calibration shows the voice signal access meeting-place lines of loudspeakers of object, when the decibel information is lower than institute When stating preset threshold and the decibel information and being more than preset duration lower than the duration of the preset threshold, by the calibration exhibition Show that the voice signal of object cuts out meeting-place lines of loudspeakers.
4. with no paper meeting according to claim 2 shows that object determines method, which is characterized in that the preset condition is also Include:
After the calibration shows the voice signal access meeting-place lines of loudspeakers of object, when real from the voice signal When extract obtain institute's semantic information in include at least one be pre-stored in the presetting database when forbidding keyword, will The calibration shows that the voice signal of object cuts out meeting-place lines of loudspeakers.
5. showing that object determines method according to the described in any item with no paper meetings of claim 2 to 4, which is characterized in that described Accessing keyword includes at least one of respect language, preset session topic word and preset key vocabulary.
6. with no paper meeting according to any one of claims 1 to 4 shows that object determines method, which is characterized in that described Method further includes following steps:
Control meeting-place video camera shooting picture signal corresponding with the calibration displaying object that the voice signal indicates, and will The access of described image signal can field display route.
7. with no paper meeting according to claim 6 shows that object determines method, which is characterized in that the method also includes Following steps:
When there is the corresponding different multiway images signal access meeting field display routes for showing object, according to described image signal Quantity will the screen of field display be divided into multiple regions, and multichannel described image signal is projected to respectively corresponding described Region.
8. a kind of with no paper meeting shows object determining device, which is characterized in that described device includes:
Module is obtained, for obtaining the voice signal that calibration shows object by microphone;
Identification module carries out speech recognition for determining the decibel information of the voice signal, and to the voice signal, extracts Obtain semantic information;
Processing module, for the decibel information and institute's semantic information to be compared with preset condition, according to comparison result Determine whether the calibration showing that the voice signal of object accesses meeting-place lines of loudspeakers.
9. a kind of with no paper meeting shows object determining device, which is characterized in that described device includes memory and processor;
The memory, for storing computer program;
The processor, for when loaded and executed, realizing no paper as described in any one of claim 1 to 7 Change meeting and shows that object determines method.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer program on the storage medium, work as institute When stating computer program and being executed by processor, realize that with no paper meeting as described in any one of claim 1 to 7 shows that object is true Determine method.
CN201910556845.1A 2019-06-25 2019-06-25 A kind of with no paper meeting shows that object determines method, apparatus and storage medium Pending CN110348011A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910556845.1A CN110348011A (en) 2019-06-25 2019-06-25 A kind of with no paper meeting shows that object determines method, apparatus and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910556845.1A CN110348011A (en) 2019-06-25 2019-06-25 A kind of with no paper meeting shows that object determines method, apparatus and storage medium

Publications (1)

Publication Number Publication Date
CN110348011A true CN110348011A (en) 2019-10-18

Family

ID=68183018

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910556845.1A Pending CN110348011A (en) 2019-06-25 2019-06-25 A kind of with no paper meeting shows that object determines method, apparatus and storage medium

Country Status (1)

Country Link
CN (1) CN110348011A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111629164A (en) * 2020-05-29 2020-09-04 联想(北京)有限公司 Video recording generation method and electronic equipment
CN114333451A (en) * 2022-01-05 2022-04-12 燕山大学 Economics teaching is with special ware of racing to be first to answer a question in wisdom classroom

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101496417A (en) * 2006-08-01 2009-07-29 雅马哈株式会社 Voice conference system
US20090220064A1 (en) * 2008-02-28 2009-09-03 Sreenivasa Gorti Methods and apparatus to manage conference calls
JP4867804B2 (en) * 2007-06-12 2012-02-01 ヤマハ株式会社 Voice recognition apparatus and conference system
CN104580776A (en) * 2015-01-16 2015-04-29 四川联友电讯技术有限公司 Telephone conference system and method capable of intelligently shielding strong noise participant based on noise detection
CN104618616A (en) * 2015-01-16 2015-05-13 四川联友电讯技术有限公司 System and method for recognizing identity of participants of conference call based on voice characteristic extraction
CN105933558A (en) * 2016-04-25 2016-09-07 四川联友电讯技术有限公司 Teleconference high-noise conference participant intelligent shielding and canceling method
CN108111701A (en) * 2016-11-24 2018-06-01 北京中创视讯科技有限公司 Silence processing method and device
CN108513063A (en) * 2018-03-19 2018-09-07 苏州科技大学 A kind of intelligent meeting camera system captured automatically
CN109309804A (en) * 2018-09-29 2019-02-05 芜湖星途机器人科技有限公司 A kind of intelligent meeting system
CN109388701A (en) * 2018-08-17 2019-02-26 深圳壹账通智能科技有限公司 Minutes generation method, device, equipment and computer storage medium
CN109783642A (en) * 2019-01-09 2019-05-21 上海极链网络科技有限公司 Structured content processing method, device, equipment and the medium of multi-person conference scene
CN109802968A (en) * 2019-01-28 2019-05-24 深圳市飞图视讯有限公司 A kind of conference speech system

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101496417A (en) * 2006-08-01 2009-07-29 雅马哈株式会社 Voice conference system
JP4867804B2 (en) * 2007-06-12 2012-02-01 ヤマハ株式会社 Voice recognition apparatus and conference system
US20090220064A1 (en) * 2008-02-28 2009-09-03 Sreenivasa Gorti Methods and apparatus to manage conference calls
CN104580776A (en) * 2015-01-16 2015-04-29 四川联友电讯技术有限公司 Telephone conference system and method capable of intelligently shielding strong noise participant based on noise detection
CN104618616A (en) * 2015-01-16 2015-05-13 四川联友电讯技术有限公司 System and method for recognizing identity of participants of conference call based on voice characteristic extraction
CN105933558A (en) * 2016-04-25 2016-09-07 四川联友电讯技术有限公司 Teleconference high-noise conference participant intelligent shielding and canceling method
CN108111701A (en) * 2016-11-24 2018-06-01 北京中创视讯科技有限公司 Silence processing method and device
CN108513063A (en) * 2018-03-19 2018-09-07 苏州科技大学 A kind of intelligent meeting camera system captured automatically
CN109388701A (en) * 2018-08-17 2019-02-26 深圳壹账通智能科技有限公司 Minutes generation method, device, equipment and computer storage medium
CN109309804A (en) * 2018-09-29 2019-02-05 芜湖星途机器人科技有限公司 A kind of intelligent meeting system
CN109783642A (en) * 2019-01-09 2019-05-21 上海极链网络科技有限公司 Structured content processing method, device, equipment and the medium of multi-person conference scene
CN109802968A (en) * 2019-01-28 2019-05-24 深圳市飞图视讯有限公司 A kind of conference speech system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111629164A (en) * 2020-05-29 2020-09-04 联想(北京)有限公司 Video recording generation method and electronic equipment
CN114333451A (en) * 2022-01-05 2022-04-12 燕山大学 Economics teaching is with special ware of racing to be first to answer a question in wisdom classroom

Similar Documents

Publication Publication Date Title
US9064160B2 (en) Meeting room participant recogniser
US20120027217A1 (en) Apparatus and method for merging acoustic object information
US11128793B2 (en) Speaker tracking in auditoriums
Stevenage et al. Interference in eyewitness and earwitness recognition
CN109474797B (en) Conference transcription system based on panoramic camera and microphone array
US8861779B2 (en) Methods for electronically analysing a dialogue and corresponding systems
JP5533854B2 (en) Speech recognition processing system and speech recognition processing method
CN107527623B (en) Screen transmission method and device, electronic equipment and computer readable storage medium
CN107211062A (en) Audio playback scheduling in virtual acoustic room
KR20120038000A (en) Method and system for determining the topic of a conversation and obtaining and presenting related content
US11650790B2 (en) Centrally controlling communication at a venue
US12052391B2 (en) Methods and systems for automatic queuing in conference calls
JP5030868B2 (en) Conference audio recording system
CN112653902A (en) Speaker recognition method and device and electronic equipment
CN110348011A (en) A kind of with no paper meeting shows that object determines method, apparatus and storage medium
JP2010109898A (en) Photographing control apparatus, photographing control method and program
CN116939150B (en) Multimedia platform monitoring system and method based on machine vision
CN112887875B (en) Conference system voice data acquisition method and device, electronic equipment and storage medium
JPH08130723A (en) Video conference system speaker discrimination device
Zekveld et al. The benefit obtained from visually displayed text from an automatic speech recognizer during listening to speech presented in noise
JP2021148854A (en) Display device, display system, computer program, and display method
CN111447400B (en) Method, device, equipment and storage medium for processing participant identification of video conference
Carragee Defining solidarity: Themes and omissions in coverage of the Solidarity trade union movement by ABC news
DE102019100403A1 (en) Method for speech processing and speech processing device
JP2014178621A (en) Information providing device and program

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20191018