CN108538299A - A kind of automatic conference recording method - Google Patents
A kind of automatic conference recording method Download PDFInfo
- Publication number
- CN108538299A CN108538299A CN201810328377.8A CN201810328377A CN108538299A CN 108538299 A CN108538299 A CN 108538299A CN 201810328377 A CN201810328377 A CN 201810328377A CN 108538299 A CN108538299 A CN 108538299A
- Authority
- CN
- China
- Prior art keywords
- content
- word
- key
- signal
- tone
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000011946 reduction process Methods 0.000 claims abstract description 5
- 230000009467 reduction Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000005236 sound signal Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- 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
- 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
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/189—Automatic justification
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Theoretical Computer Science (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Machine Translation (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention belongs to conference audio processing technology fields, disclose a kind of automatic conference recording method, including：Data acquisition, noise reduction process, tone identification, speech recognition, key content mark and Automatic Typesetting.The present invention is capable of the emphasis of automatic marking minutes, prominent session topic, and automation typesetting forms the minutes after arranging, saves the time of secondary arrangement.
Description
Technical field
The invention belongs to conference audio processing technology field more particularly to a kind of automatic conference recording methods.
Background technology
The existing higher meeting room of rank generally can all be equipped with the function of automatic conference record, i.e., is equipped in meeting room
Pick up facility is picked up the sound of speaker, and the function of word is then converted by voice, records the content of meeting,
Minutes will be formed after the meeting in this way to use for participant, in the prior art, minutes are generally relatively rough, need manpower
Secondary operation conference content could be refined either to be arranged remembered with forming the meeting that directly can use or file
Record, thus can waste of manpower, and it is time-consuming, do not form the record form of full automation.
Invention content
The embodiment of the present invention is designed to provide a kind of automatic conference recording method, is capable of automatic marking minutes
Emphasis, prominent session topic, automation typesetting form the minutes after arranging, save the time of secondary arrangement.
What the embodiment of the present invention was realized in：
A kind of automatic conference recording method, including：
The template of daily repertorie, the content of key word library and meeting typesetting is set；
The indoor voice signal of meeting is picked up, and converts voice signal to corresponding analog electrical signal, then will simulation electricity
Signal is converted into digital signal, carries out noise reduction process to the digital signal, exports the voice signal after noise reduction, while detecting letter
Number Strength Changes, if signal strength increases suddenly, by the continuous signal of the section labeled as the tone aggravate content and/or
Signal in the fixation period after change in signal strength is aggravated into content labeled as the tone；
By the transmission of sound signals after noise reduction to cloud server, language and characters identification is provided in the cloud server
Function calls the language and characters identification function that the voice signal after noise reduction is identified, and returns to corresponding word content；
The tone is aggravated the corresponding word content of content to be marked, the tone as minutes is reinforced in emphasis
Hold；The word content of return is handled, it is word at least three times to search the frequency of occurrences, calls the content of daily repertorie,
If the word is the word in non-daily repertorie, word key content label is carried out to the word；To in the word of return
Appearance handled, the content in search key library in word content, if there is the content of key word library, then to the content into
Row keyword key content marks；
In chronological order, it calls the template of meeting typesetting to carry out typesetting to all word contents, the tone is reinforced into emphasis
Content, word key content and keyword key content are marked in the content of typesetting.
The embodiment of the present invention is by speech recognition, tone identification, keyword recognition and the identification of Fei terms to conference content
It is recorded, forms document, key content is marked, and Automatic Typesetting, realize the function of automatic conference record, reduce people
The secondary finishing time and difficulty of power, are capable of the emphasis of automatic marking minutes, prominent session topic, and automation typesetting is formed
Minutes after arrangement.
Description of the drawings
Fig. 1 is the hardware block diagram that the present invention realizes automatic conference recording method；
Fig. 2 is the flow chart that the present invention realizes automatic conference recording method.
Specific implementation mode
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
The specific implementation of the present invention is described in detail below in conjunction with specific embodiment：
As depicted in figs. 1 and 2, realize that the hardware of automatic conference recording method of the present invention includes mainly three modules, it is transaudient
Device, DSP (Digital Signal Processing digital signal processors) and cloud server, microphone is for picking up meeting
Indoor sound is discussed, the voice signal of participant is acquired, voice signal is converted to analog electrical signal, is turned containing A/D in DSP
Block is changed the mold, analog electrical signal is then converted to by digital signal by A/D conversion modules, noise etc. is eliminated by DSP processing
After interference signal, voice is called to know to cloud server, then by cloud server the signal transmission after DSP processing
Other function (such as speech recognition API of HKUST News), is then back to letter signal, letter signal is finally carried out typesetting, is passed through
Processing, it will the content of Special attention will be given to is labeled in view, the process for the entire automatic conference record thus completed.It is specific real
Existing method approximately as：
Data acquire：Data acquisition is carried out to the voice signal of participant, mainly analog signal is converted to digital letter
Number.
Noise reduction process：The number being mainly converted to data acquisition performs some processing, and mainly carries out noise reduction, letter
Number it is processed into the signal that can be easier carrying out speech recognition below.
The tone identifies：The tone identification of participant is identified, it is mainly relevant in key content mark below,
It detects that the tone aggravates, is that participant indicates one that wants key content to be emphasized.
Speech recognition：Voice signal is converted to letter signal.
Key content marks：To some in this meeting, crucial content is labeled, and is mainly embodied in language above
Gas identification frequently uses in meeting, but the word of non-day term is labeled, and the also subsequent content of some keywords is into rower
Note, such as：The subsequent content of " I it is however emphasized that " followed by.
Automatic Typesetting：Typesetting is carried out to the content of current meeting, shows which content is that who participant delivers,
And the chronological order delivered.
A kind of automatic conference recording method, including：
The template of daily repertorie, the content of key word library and meeting typesetting is set；It can be provided with, locate in dsp
It is directly invoked during reason；
The indoor voice signal of meeting is picked up, and converts voice signal to corresponding analog signal, then by analog signal
It is converted into digital signal, noise reduction process is carried out to the digital signal, exports the voice signal after noise reduction, while detecting signal
The continuous signal of the section is being aggravated content labeled as the tone and/or will believed by Strength Changes if signal strength increases suddenly
The signal in the fixation period after number Strength Changes aggravates content labeled as the tone；If sound increases, show the language of speaker
Gas can aggravate, it is more likely that be the content that speaker wants emphasis expression, after marking in this way, be formed by meeting note later
Record can obtain the concern of user；
By the transmission of sound signals after noise reduction to cloud server, language and characters identification is provided in the cloud server
Function calls the language and characters identification function that the voice signal after noise reduction is identified, and returns to corresponding word content；
The tone is aggravated the corresponding word content of content to be marked, the tone as minutes is reinforced in emphasis
Hold；The word content of return is handled, it is word at least three times to search the frequency of occurrences, calls the content of daily repertorie,
If the word is the word in non-daily repertorie, word key content label is carried out to the word；To in the word of return
Appearance handled, the content in search key library in word content, if there is the content of key word library, then to the content into
Row keyword key content marks；Here, day term includes person " you, I, he " etc., for daily repertorie and key word library
And layout template, these can be configured according to the type of meeting, can change at any time, automatically form meeting in this way
More targetedly also just properer requirement can be recorded when record；
In chronological order, it calls the template of meeting typesetting to carry out typesetting to all word contents, the tone is reinforced into emphasis
Content, word key content and keyword key content are marked in the content of typesetting.It is general to wrap about the template of typesetting
The parts such as session topic, time, place, content, key content are included, the tone reinforces key content, word key content and key
Word key content is placed in key content this part, is conducive to emphasis reading in this way.
In the embodiment of the present invention, automatic conference record is mainly handled the data of microphone pick, by voice
Signal is converted to word, then typesetting at document.Automatic conference record is by hardware with having speech recognition, at natural language
The software of reason ability combines, and realizes that minutes, automatic conference record save prodigious human resources, and can be clear
The clear viewpoint recorded participant and delivered, does not have ignored pith therein, this is that traditional artificial minutes can not
Analogy.By microphone by the sound collection of participant, by certain processing, format conversion, sound is believed in speech recognition
Then number conversion words carry out Automatic Typesetting, the processing such as automatic marking to word, generate minutes document at letter signal.This
The automatic conference recording method of invention solves in automatic conference record, can not be to content that participant highlights into rower
The problem of note, it is ensured that theme is clear in meeting, and major issue will not omit.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to restrict the invention, all essences in the present invention
All any modification, equivalent and improvement etc., should all be included in the protection scope of the present invention made by within refreshing and principle.
Claims (1)
1. a kind of automatic conference recording method, which is characterized in that including：
The template of daily repertorie, the content of key word library and meeting typesetting is set；
The indoor voice signal of meeting is picked up, and converts voice signal to corresponding analog electrical signal, then by analog electrical signal
It is converted into digital signal, noise reduction process is carried out to the digital signal, exports the voice signal after noise reduction, while detecting signal
The continuous signal of the section is being aggravated content labeled as the tone and/or will believed by Strength Changes if signal strength increases suddenly
The signal in the fixation period after number Strength Changes aggravates content labeled as the tone；
By the transmission of sound signals after noise reduction to cloud server, language and characters identification work(is provided in the cloud server
Can, call the language and characters identification function that the voice signal after noise reduction is identified, and return to corresponding word content；
The tone is aggravated the corresponding word content of content to be marked, the tone as minutes reinforces key content；
The word content of return is handled, it is word at least three times to search the frequency of occurrences, calls the content of daily repertorie, if
The word is the word in non-daily repertorie, then carries out word key content label to the word；To the word content of return into
Row processing, the content in search key library in word content then close the content if there is the content of key word library
Key word key content marks；
In chronological order, the template of meeting typesetting is called to carry out typesetting to all word content, by the tone reinforce key content,
Word key content and keyword key content are marked in the content of typesetting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810328377.8A CN108538299A (en) | 2018-04-11 | 2018-04-11 | A kind of automatic conference recording method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810328377.8A CN108538299A (en) | 2018-04-11 | 2018-04-11 | A kind of automatic conference recording method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108538299A true CN108538299A (en) | 2018-09-14 |
Family
ID=63480185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810328377.8A Pending CN108538299A (en) | 2018-04-11 | 2018-04-11 | A kind of automatic conference recording method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108538299A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109817225A (en) * | 2019-01-25 | 2019-05-28 | 广州富港万嘉智能科技有限公司 | A kind of location-based meeting automatic record method, electronic equipment and storage medium |
| CN114254076A (en) * | 2021-12-16 | 2022-03-29 | 天翼爱音乐文化科技有限公司 | Audio processing method, system and storage medium for multimedia teaching |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2320333A3 (en) * | 2009-11-06 | 2012-06-20 | Ricoh Company, Ltd. | Comment recording appartus, method, program, and storage medium |
| CN103165131A (en) * | 2011-12-17 | 2013-06-19 | 富泰华工业（深圳）有限公司 | Voice processing system and voice processing method |
| CN105810207A (en) * | 2014-12-30 | 2016-07-27 | 富泰华工业（深圳）有限公司 | Meeting recording device and method thereof for automatically generating meeting record |
| CN106024009A (en) * | 2016-04-29 | 2016-10-12 | 北京小米移动软件有限公司 | Audio processing method and device |
| CN107562723A (en) * | 2017-08-24 | 2018-01-09 | 网易乐得科技有限公司 | Meeting processing method, medium, device and computing device |
| CN107845422A (en) * | 2017-11-23 | 2018-03-27 | 郑州大学第附属医院 | A kind of remote medical consultation with specialists session understanding and method of abstracting based on the fusion of multi-modal clue |
-
2018
- 2018-04-11 CN CN201810328377.8A patent/CN108538299A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2320333A3 (en) * | 2009-11-06 | 2012-06-20 | Ricoh Company, Ltd. | Comment recording appartus, method, program, and storage medium |
| CN103165131A (en) * | 2011-12-17 | 2013-06-19 | 富泰华工业（深圳）有限公司 | Voice processing system and voice processing method |
| CN105810207A (en) * | 2014-12-30 | 2016-07-27 | 富泰华工业（深圳）有限公司 | Meeting recording device and method thereof for automatically generating meeting record |
| CN106024009A (en) * | 2016-04-29 | 2016-10-12 | 北京小米移动软件有限公司 | Audio processing method and device |
| CN107562723A (en) * | 2017-08-24 | 2018-01-09 | 网易乐得科技有限公司 | Meeting processing method, medium, device and computing device |
| CN107845422A (en) * | 2017-11-23 | 2018-03-27 | 郑州大学第附属医院 | A kind of remote medical consultation with specialists session understanding and method of abstracting based on the fusion of multi-modal clue |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109817225A (en) * | 2019-01-25 | 2019-05-28 | 广州富港万嘉智能科技有限公司 | A kind of location-based meeting automatic record method, electronic equipment and storage medium |
| CN114254076A (en) * | 2021-12-16 | 2022-03-29 | 天翼爱音乐文化科技有限公司 | Audio processing method, system and storage medium for multimedia teaching |
| CN114254076B (en) * | 2021-12-16 | 2023-03-07 | 天翼爱音乐文化科技有限公司 | Audio processing method, system and storage medium for multimedia teaching |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN207149252U (en) | Speech processing system | |
| CN110335612A (en) | Minutes generation method, device and storage medium based on speech recognition | |
| CN108305632A (en) | A kind of the voice abstract forming method and system of meeting | |
| CN110751943A (en) | Voice emotion recognition method and device and related equipment | |
| CN107799117A (en) | Key message is identified to control the method, apparatus of audio output and audio frequency apparatus | |
| Morgan et al. | Meetings about meetings: research at ICSI on speech in multiparty conversations | |
| CN109887508A (en) | A kind of meeting automatic record method, electronic equipment and storage medium based on vocal print | |
| CN104883437B (en) | The method and system of speech analysis adjustment reminding sound volume based on environment | |
| CN105244042B (en) | A kind of speech emotional interactive device and method based on finite-state automata | |
| WO2020155490A1 (en) | Method and apparatus for managing music based on speech analysis, and computer device | |
| CN103165131A (en) | Voice processing system and voice processing method | |
| CN111683317B (en) | Prompting method and device applied to earphone, terminal and storage medium | |
| CN109040484A (en) | A kind of Auto-matching contact staff method | |
| CN107591150A (en) | Audio recognition method and device, computer installation and computer-readable recording medium | |
| CN108538299A (en) | A kind of automatic conference recording method | |
| US20200265843A1 (en) | Speech broadcast method, device and terminal | |
| CN106302933A (en) | Voice information whose processing method and terminal | |
| CN107274876A (en) | A kind of audition paints spectrometer | |
| CN109817225A (en) | A kind of location-based meeting automatic record method, electronic equipment and storage medium | |
| CN109346057A (en) | A kind of speech processing system of intelligence toy for children | |
| CN113129866B (en) | Voice processing method, device, storage medium and computer equipment | |
| CN101867742A (en) | Television system based on sound control | |
| CN107277276A (en) | One kind possesses voice control function smart mobile phone | |
| CN110246502A (en) | Voice de-noising method, device and terminal device | |
| TW201207838A (en) | Electronic recording apparatus and method thereof |
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: 20180914 |