CN110263313A - A kind of man-machine coordination edit methods for meeting shorthand - Google Patents
A kind of man-machine coordination edit methods for meeting shorthand Download PDFInfo
- Publication number
- CN110263313A CN110263313A CN201910533479.8A CN201910533479A CN110263313A CN 110263313 A CN110263313 A CN 110263313A CN 201910533479 A CN201910533479 A CN 201910533479A CN 110263313 A CN110263313 A CN 110263313A
- Authority
- CN
- China
- Prior art keywords
- audio
- text
- meeting
- audio section
- terminal
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012937 correction Methods 0.000 claims abstract description 4
- 238000003058 natural language processing Methods 0.000 claims description 23
- 238000005520 cutting process Methods 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 230000003362 replicative effect Effects 0.000 claims 1
- 238000006243 chemical reaction Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 230000009466 transformation Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input 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
- G06F3/16—Sound input; Sound output
- G06F3/165—Management of the audio stream, e.g. setting of volume, audio stream path
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input 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
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C7/00—Arrangements for writing information into, or reading information out from, a digital store
- G11C7/16—Storage of analogue signals in digital stores using an arrangement comprising analogue/digital [A/D] converters, digital memories and digital/analogue [D/A] converters
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Acoustics & Sound (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Telephonic Communication Services (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention discloses a kind of man-machine coordination edit methods for meeting shorthand, the following steps are included: 1. meetings shorthand terminal cuts audio stream according to natural sentences, and audio section is sent to third-party server, audio section is converted to corresponding text by third-party server；2. meeting takes down in short-hand terminal when cut audio stream, to each audio section at the beginning of, end time, Audiocode record, and combine the corresponding text generation journal file of the audio section of third-party server return；3. terminal is taken down in short-hand in meeting is sent to collaborative editing server for audio section, text and journal file；4. collaborative editing server corresponds audio section and text according to journal file；5. the artificial correction that human-edited's terminal is used to carry out minutes according to one-to-one audio section and text.The present invention can simply and easily according to conference audio to the minutes of dynamic generation real-time amendment.
Description
Technical field
The present invention relates to voice stenography technical field, especially a kind of man-machine coordination edit methods for meeting shorthand.
Background technique
In conference process, the hoc scenario and particular content of meeting are recorded by record personnel, are formed meeting
View record.Most traditional form is to arrange verification meeting by record personnel on site shorthand and according to session recording after meeting adjourned
View record.
With the development of speech recognition technology (ASR) and natural language processing technique (NLP), the audio energy that is generated in meeting
It is enough to be directly converted into text in real time at meeting scene and generate minutes, considerably reduce the workload of record personnel.
Speech recognition technology be by the vocabulary Content Transformation in human speech be computer-readable input, such as key,
Binary coding or character string；Natural language processing technique research how is realized between people and computer with nature language
Speech carries out efficient communication；The two combines, it will be able to which human speech is converted to the wirtiting form of human language --- text
This.But this conversion process cannot be guaranteed very precisely, particularly with some terms without in input system, personage
Name etc., system have no idea to judge should be specifically what word.Such as input voice " Zhang Ziyi ", system is for this star's
Name can be recognized and converted into correct text；It inputs voice " Zhang Erlei ", for this strange phrase, system is only
Can word for word transliteration and select system be arranged default option, as system default " zhang " preferentially " chapter " when, voice " Zhang Erlei " can
It can will be converted into text " Zhang Erlei ", which results in the presence of mistake.Certainly, actual mistake is not limited only to this.
The accuracy rate of the existing man-machine coordination edit methods for meeting shorthand is substantially in 90-95% or so, for text
Present in mistake, it is necessary to be modified.Currently, the correcting mode used, after mainly still meeting adjourned, records personnel
Arrangement verification is carried out to minutes according to session recording, so that minutes generating there are certain time delay at original text, deposits
In certain inconvenience.It is readily apparent that, optimal correcting mode, text made of audio conversion is carried out therewith certainly
Real time modifying, but existing technology barrier is, how to realize one side audio just in typing, one side text is generating same
When, text in time, rapidly correct, that is, how to repair the text progress just in dynamic generation in time, rapidly
Just.
Summary of the invention
In view of the above-mentioned problems, the present invention provides a kind of man-machine coordination edit methods for meeting shorthand.
A kind of man-machine coordination edit methods for meeting shorthand, comprising the following steps: when 1. meetings carry out, meeting shorthand
Terminal carries out cutting to audio stream according to natural sentences and forms audio section, and audio section is sent to third-party server, third party
Audio section is converted to corresponding text by speech recognition technology and natural language processing technique by server；2. meeting is fast
Remember terminal when cutting audio stream, to each audio section at the beginning of, end time, Audiocode record, and combine
The corresponding text generation journal file of the audio section that third-party server returns；3. meeting takes down in short-hand terminal for audio section, text
Collaborative editing server is sent to journal file；4. collaborative editing server carries out audio section and text according to journal file
It corresponds；5. the artificial correction that human-edited's terminal is used to carry out minutes according to one-to-one audio section and text.
Further, third-party server includes ASR server and NLP server.
Further, audio section duration is limited within 60s, and cutting the time interval between audio section is 0.00001ms.
Further, every a segment of audio and text is numbered in meeting shorthand terminal；If audio section does not have corresponding text
This, meeting shorthand terminal is marked in journal file.
Further, when meeting shorthand terminal detects network interruption, stop sending data to third-party server, and
Data are temporarily deposited in memory, when network is again coupled to, data are orderly sent to by third-party server by memory.
Further, it while meeting shorthand terminal cutting audio stream, replicates audio stream and is sent to collaborative editing service
Device.
Further, human-edited's terminal has lookup, replacement function, can directly modify some text or phrase,
The identical mistake in text can disposably be corrected by searching for replacement, and current modified content can be carried out
Special display, for record, personnel are checked.
Beneficial effects of the present invention: 1. meetings shorthand terminal transmits audio in the form of audio section, short and small audio section
After the end of transmission, text conversion, the text after conversion can be modified, to realize the meeting to dynamic generation
The real-time amendment of record；2. the one-to-one correspondence of audio and text according to natural sentences for unit is realized, so that the record direct point of personnel
A certain section of text is hit, the corresponding audio of this section of text can play back, and record personnel is assisted to carry out judgement and text amendment；3.
Treatment mechanism when suspension is coped with, the audio after capable of well solving network reconnection sends problem.
Detailed description of the invention
Fig. 1 is that system block diagram is taken down in short-hand in meeting；
Fig. 2 is audio volume control schematic diagram.
Specific embodiment
The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.The embodiment of the present invention is
It is provided for the sake of example and description, and is not exhaustively or to limit the invention to disclosed form.Very much
Modifications and variations are obvious for the ordinary skill in the art.Selection and description embodiment are in order to more preferable
Illustrate the principle of the present invention and practical application, and makes those skilled in the art it will be appreciated that the present invention is suitable to design
In the various embodiments with various modifications of special-purpose.
Embodiment 1
A kind of man-machine coordination edit methods for meeting shorthand, the hardware device being mentioned to have meeting to take down in short-hand terminal, third party
Server, collaborative editing server, human-edited's terminal.In the present embodiment, third-party server include ASR server and
NLP server.The direct connection relationship of hardware device is as shown in Figure 1.
Meeting shorthand terminal is disposed on meeting scene, is included and pretreated autonomous device to conference audio；People
Work editor terminal is the equipment such as the desktop computer for being mounted with specific software, notebook, and the specific software refers to can be realized it
The software of necessary functions.
Human-edited's terminal and meeting shorthand terminal can be located at different location, such as meeting in Beijing,
Record personnel carry out the amendment of minutes in Shanghai.
Meeting shorthand terminal, ASR server, NLP server, the connection type between human-edited's terminal can use but
It is not limited to cable network, WiFi network, 4G network.
Man-machine coordination edit methods disclosed in the present embodiment, comprising the following steps:
One, when meeting carries out, meeting, which takes down in short-hand terminal and carries out cutting to audio stream according to natural sentences, forms audio section, and by audio section
It is sent to third-party server, third-party server is converted audio section by speech recognition technology and natural language processing technique
For corresponding text.
Third-party server includes ASR server and NLP server, and meeting takes down in short-hand terminal and audio section is sent to ASR clothes
Business device, ASR server is by audio section Content Transformation Cheng Yici text and is back to meeting shorthand terminal, and meeting shorthand terminal again will
The text that ASR server returns is sent to NLP server, and NLP server is used for a text for generating ASR server
It is automatically corrected according to natural language, and revised secondary text is back to meeting shorthand terminal.
ASR server is mechanical conversion in this conversion process by audio section Content Transformation Cheng Yici text, wherein
There are wrong word quite a lot (mostly unisonance character errors)；NLP server carries out a text according to natural language automatic
Amendment, this conversion process are namely based on the habit of Human Natural Language, and the process of automatic error-correcting is carried out to a text.NLP
Server is back to the secondary text of meeting shorthand terminal, and accuracy is up to 90-95%, but there are still certain error rates.
People has pause when normally speaking, and the natural sentences in the present embodiment refer to this sentence between adjacent pause
Words, such as " thick mad sound my that the Yellow River " in Fig. 2, " not only ringing in the mansion of the United Nations ".It is carried out according to natural sentences
Audio stream cutting, first is that with can guaranteeing audio-frequency information integrality, the case where preventing audio data from losing；Second is that reducing sound
The bandwidth occupied in frequency transmission process quickly reaches speech text change server convenient for audio, reduces because network traffic congestion causes
Audio is jammed in the road for being sent to speech text change server, this like on the road of a congestion, bicycle,
Battery truck, especially pedestrian can shuttle from automobile gap, and network transmission is similarly.
It fluctuates when detecting in a period of time without audio, just audio stream is cut, it is then subsequent in 0.00001ms
It is continuous to start to process.It will be set to 0.00001ms between audio section, is loss and mistake in order to reduce audio as far as possible
Position.For example, be averaged if being divided into 0.1ms between audio section comprising an audio section interval among 5s audio, 1h audio meeting
72ms deviation is generated, the deviation that 4h audio generates reaches 288ms；If being divided into 0.00001ms between audio section, it is averaged, 1h sound
Frequency only generates 0.0072ms deviation, and the deviation that 4h audio generates is also only 0.0288ms.
If all not detecting pause prolonged enough in 60s, audio stream is cut by force, is avoided
Audio section is too long, influences the transmission speed of audio section and the response speed of ASR server and NLP server.
When audio stream is cut to form audio section, it is with the audio stream that is generating with regard to independent, it is meant that this section
The end of audio, this section audio can be played back by also implying that, convenient for being modified to its corresponding text.
Two, meeting take down in short-hand terminal when cutting audio stream, to each audio section at the beginning of, end time, audio generation
Code is recorded, and the corresponding text generation journal file of the audio section for combining third-party server to return.Here the audio
The corresponding text of section refers to NLP server revised text automatically.
At the beginning of audio section, the end time is subject to Beijing time.At the beginning of audio section, the end time,
And its corresponding Audiocode is the information that meeting shorthand terminal can obtain in audio cutting process, but audio section pair
The text answered is the secondary text that NLP server returns.
Ideally, a segment of audio corresponds to passage, carries out corresponding in sequence, but there may be one section
Audio does not correspond to a possibility that text, such as situations such as live play song.What this related to how to return to NLP server
The problem of secondary text and audio section correspond.In the present embodiment, solution to this problem is, if audio section not with
Corresponding text, meeting shorthand terminal is marked in journal file, and collaborative editing server is according to journal file by sound
Frequency range and secondary text are corresponded, if encountering some audio section has label, are just skipped, in order to avoid there is text
The problem of mistake corresponding with audio section occurs.How meeting shorthand terminal knows which section audio section does not have corresponding text, this
It is the data judgement returned by ASR server, such as time started, end time, audio is numbered into one such information
Or much information carries out fusion and forms characteristic information connection audio section sending jointly to ASR server, ASR server, which returns, to be carried
Text of this feature information, meeting shorthand terminal can know that this audio section is sended over either with or without corresponding text.
Three, audio section, text and journal file are sent to collaborative editing server, collaborative editing clothes by meeting shorthand terminal
Business device corresponds audio section and text according to journal file.
In the transmission process of audio section and text, audio section is big and text is small, therefore text is often earlier than audio section
Ground is transferred to collaborative editing server, i.e., simultaneously nonsimultaneous transmission takes to collaborative editing server, collaborative editing for audio section and text
How business device knows which section text will be corresponding to which section audio.In the present embodiment, terminal is taken down in short-hand to each section by meeting
Audio and text are numbered to solve the problems, such as this.
Four, human-edited's terminal is used to carry out the artificial correction of minutes according to one-to-one audio section and text.
For ease of operation, segmentation can be carried out to text according to audio section to show, i.e. the corresponding text of an audio section
It is shown as one section.When record personnel click certain section of text manually, human-edited's terminal gives the corresponding audio volume control of this section of text
It is selected with frame and shows and play, record personnel is assisted to carry out judgement and text amendment.For example, " loudly shouting Chinese obtain when clicking
Point ", then the corresponding audio volume control of this section of text is selected by frame and shows and play.
At the same time, human-edited's terminal has lookup, replacement function, can directly modify some text or phrase,
The identical mistake in text can disposably be corrected by searching for replacement, and current modified content can be carried out
Special display, for record, personnel are checked.
Since meeting shorthand terminal, ASR server, NLP server, collaborative editing server, human-edited's terminal are all
By network connection, during meeting carries out, it may occur however that the case where network interruption.When meeting shorthand terminal detects in network
When disconnected, stop sending data to ASR server/NLP server, and data are temporarily deposited in memory, when network connects again
When connecing, data are orderly sent to ASR server/NLP server by memory, after avoiding network reconnection, ASR server/NLP
Server centered receives audio data, is mistakenly considered by attack, and closes meeting shorthand terminal and the connection between it.For
Prevent offline condition occur between meeting shorthand terminal and collaborative editing server, collaborative editing server memory has the meeting of backup
Discuss audio.The conference audio of backup can be used for after the conference is over, and human-edited's terminal transfers conference audio to minutes again
It is modified, rather than minutes must be modified in conference process；It is also possible to prevent meeting from taking down in short-hand terminal
There is the problem of when transmitting obstacle, human-edited's terminal can not obtain audio-frequency information generation between collaborative editing server.
Obviously, described embodiment is only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, this field and those of ordinary skill in the related art institute without creative labor
The every other embodiment obtained, all should belong to the scope of protection of the invention.
Claims (8)
1. a kind of man-machine coordination edit methods for meeting shorthand, which comprises the following steps:
Step 1, when meeting carries out, meeting, which takes down in short-hand terminal and carries out cutting to audio stream according to natural sentences, forms audio section, and by sound
Frequency range is sent to third-party server, and third-party server passes through speech recognition technology and natural language processing technique for audio section
Be converted to corresponding text；
Step 2, meeting take down in short-hand terminal when cutting audio stream, to each audio section at the beginning of, end time, Audiocode
The corresponding text generation journal file of the audio section for being recorded, and third-party server being combined to return；
Step 3, meeting takes down in short-hand terminal and audio section, text and journal file is sent to collaborative editing server；
Step 4, collaborative editing server corresponds audio section and text according to journal file；
Step 5, human-edited's terminal is used to carry out the artificial correction of minutes according to one-to-one audio section and text.
2. man-machine coordination edit methods according to claim 1, which is characterized in that third-party server includes ASR service
Device and NLP server.
3. man-machine coordination edit methods according to claim 1 or 2, which is characterized in that audio section duration be limited in 60s with
Interior, cutting the time interval between audio section is 0.00001ms.
4. man-machine coordination edit methods according to claim 3, which is characterized in that meeting takes down in short-hand terminal to every a segment of audio
It is numbered with text.
5. man-machine coordination edit methods according to claim 3, which is characterized in that if audio section does not have corresponding text,
Meeting shorthand terminal is marked in journal file.
6. according to claim 1,2,4,5 described in any item man-machine coordination edit methods, which is characterized in that when meeting is taken down in short-hand eventually
When end detects network interruption, stops sending data to third-party server, and data are temporarily deposited in memory, work as network
When being again coupled to, data are orderly sent to by third-party server by memory.
7. man-machine coordination edit methods according to claim 6, which is characterized in that terminal cutting audio stream is taken down in short-hand in meeting
Meanwhile it replicating audio stream and being sent to collaborative editing server.
8. man-machine coordination edit methods according to claim 1, which is characterized in that human-edited's terminal, which has, searches, replaces
Change function, can directly modify some text or phrase, can also by searching for replacement in text it is identical mistake into
The disposable amendment of row, and Special display can be carried out to current modified content, for record, personnel are checked.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910533479.8A CN110263313B (en) | 2019-06-19 | 2019-06-19 | Man-machine collaborative editing method for conference shorthand |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910533479.8A CN110263313B (en) | 2019-06-19 | 2019-06-19 | Man-machine collaborative editing method for conference shorthand |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110263313A true CN110263313A (en) | 2019-09-20 |
| CN110263313B CN110263313B (en) | 2021-08-24 |
Family
ID=67919636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910533479.8A Active CN110263313B (en) | 2019-06-19 | 2019-06-19 | Man-machine collaborative editing method for conference shorthand |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110263313B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113421572A (en) * | 2021-06-23 | 2021-09-21 | 平安科技（深圳）有限公司 | Real-time audio conversation report generation method and device, electronic equipment and storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101101590A (en) * | 2006-07-04 | 2008-01-09 | 王建波 | Sound and character correspondence relation table generation method and positioning method |
| US20090150139A1 (en) * | 2007-12-10 | 2009-06-11 | Kabushiki Kaisha Toshiba | Method and apparatus for translating a speech |
| CN105159870A (en) * | 2015-06-26 | 2015-12-16 | 徐信 | Processing system for precisely completing continuous natural speech textualization and method for precisely completing continuous natural speech textualization |
| US20160189713A1 (en) * | 2014-12-30 | 2016-06-30 | Hon Hai Precision Industry Co., Ltd. | Apparatus and method for automatically creating and recording minutes of meeting |
| CN105827417A (en) * | 2016-05-31 | 2016-08-03 | 安徽声讯信息技术有限公司 | Voice quick recording device capable of performing modification at any time in conference recording |
| CN105845129A (en) * | 2016-03-25 | 2016-08-10 | 乐视控股（北京）有限公司 | Method and system for dividing sentences in audio and automatic caption generation method and system for video files |
| CN106057193A (en) * | 2016-07-13 | 2016-10-26 | 深圳市沃特沃德股份有限公司 | Conference record generation method based on telephone conference and device |
| CN106802885A (en) * | 2016-12-06 | 2017-06-06 | 乐视控股（北京）有限公司 | A kind of meeting summary automatic record method, device and electronic equipment |
| CN106941000A (en) * | 2017-03-21 | 2017-07-11 | 百度在线网络技术（北京）有限公司 | Voice interactive method and device based on artificial intelligence |
| CN106971723A (en) * | 2017-03-29 | 2017-07-21 | 北京搜狗科技发展有限公司 | Method of speech processing and device, the device for speech processes |
| CN107451110A (en) * | 2017-07-10 | 2017-12-08 | 珠海格力电器股份有限公司 | Method, device and server for generating conference summary |
| CN108008824A (en) * | 2017-12-26 | 2018-05-08 | 安徽声讯信息技术有限公司 | The method that official document takes down in short-hand the collection of this multilink data |
| CN108335697A (en) * | 2018-01-29 | 2018-07-27 | 北京百度网讯科技有限公司 | Minutes method, apparatus, equipment and computer-readable medium |
-
2019
- 2019-06-19 CN CN201910533479.8A patent/CN110263313B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101101590A (en) * | 2006-07-04 | 2008-01-09 | 王建波 | Sound and character correspondence relation table generation method and positioning method |
| US20090150139A1 (en) * | 2007-12-10 | 2009-06-11 | Kabushiki Kaisha Toshiba | Method and apparatus for translating a speech |
| US20160189713A1 (en) * | 2014-12-30 | 2016-06-30 | Hon Hai Precision Industry Co., Ltd. | Apparatus and method for automatically creating and recording minutes of meeting |
| CN105159870A (en) * | 2015-06-26 | 2015-12-16 | 徐信 | Processing system for precisely completing continuous natural speech textualization and method for precisely completing continuous natural speech textualization |
| CN105845129A (en) * | 2016-03-25 | 2016-08-10 | 乐视控股（北京）有限公司 | Method and system for dividing sentences in audio and automatic caption generation method and system for video files |
| CN105827417A (en) * | 2016-05-31 | 2016-08-03 | 安徽声讯信息技术有限公司 | Voice quick recording device capable of performing modification at any time in conference recording |
| CN106057193A (en) * | 2016-07-13 | 2016-10-26 | 深圳市沃特沃德股份有限公司 | Conference record generation method based on telephone conference and device |
| CN106802885A (en) * | 2016-12-06 | 2017-06-06 | 乐视控股（北京）有限公司 | A kind of meeting summary automatic record method, device and electronic equipment |
| CN106941000A (en) * | 2017-03-21 | 2017-07-11 | 百度在线网络技术（北京）有限公司 | Voice interactive method and device based on artificial intelligence |
| CN106971723A (en) * | 2017-03-29 | 2017-07-21 | 北京搜狗科技发展有限公司 | Method of speech processing and device, the device for speech processes |
| CN107451110A (en) * | 2017-07-10 | 2017-12-08 | 珠海格力电器股份有限公司 | Method, device and server for generating conference summary |
| CN108008824A (en) * | 2017-12-26 | 2018-05-08 | 安徽声讯信息技术有限公司 | The method that official document takes down in short-hand the collection of this multilink data |
| CN108335697A (en) * | 2018-01-29 | 2018-07-27 | 北京百度网讯科技有限公司 | Minutes method, apparatus, equipment and computer-readable medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113421572A (en) * | 2021-06-23 | 2021-09-21 | 平安科技（深圳）有限公司 | Real-time audio conversation report generation method and device, electronic equipment and storage medium |
| CN113421572B (en) * | 2021-06-23 | 2024-02-02 | 平安科技（深圳）有限公司 | Real-time audio dialogue report generation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110263313B (en) | 2021-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10614173B2 (en) | Auto-translation for multi user audio and video | |
| US10885318B2 (en) | Performing artificial intelligence sign language translation services in a video relay service environment | |
| US9710819B2 (en) | Real-time transcription system utilizing divided audio chunks | |
| CN106409283B (en) | Man-machine mixed interaction system and method based on audio | |
| CN110557451B (en) | Dialogue interaction processing method and device, electronic equipment and storage medium | |
| US8140634B2 (en) | Interactive text communication system | |
| CN110392168B (en) | Call processing method, device, server, storage medium and system | |
| CN109147779A (en) | Voice data processing method and device | |
| US20120072845A1 (en) | System and method for classifying live media tags into types | |
| CN110265026A (en) | A kind of meeting shorthand system and meeting stenography method | |
| CN104010267A (en) | Method and system for supporting a translation-based communication service and terminal supporting the service | |
| US20120259924A1 (en) | Method and apparatus for providing summary information in a live media session | |
| CN109005190B (en) | Method for realizing full duplex voice conversation and page control on webpage | |
| CN106059895A (en) | Collaborative task generation method, apparatus and system | |
| CN101834809B (en) | Internet instant message communication system | |
| CN109327609A (en) | Incoming call Intelligent treatment method and system based on handset call transfer and wechat, public platform or small routine | |
| US12159632B2 (en) | Automated audio-to-text transcription in multi-device teleconferences | |
| US20080205279A1 (en) | Method, Apparatus and System for Accomplishing the Function of Text-to-Speech Conversion | |
| US11580954B2 (en) | Systems and methods of handling speech audio stream interruptions | |
| CN110263313A (en) | A kind of man-machine coordination edit methods for meeting shorthand | |
| US8195457B1 (en) | System and method for automatically sending text of spoken messages in voice conversations with voice over IP software | |
| CN110265027A (en) | A kind of audio frequency transmission method for meeting shorthand system | |
| CN110264998A (en) | A kind of audio localization method for meeting shorthand system | |
| CN111400467B (en) | Robot chatting method | |
| US20240233745A1 (en) | Performing artificial intelligence sign language translation services in a video relay service environment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |