CN106782506A - A kind of method that recorded audio is divided into section - Google Patents
A kind of method that recorded audio is divided into section Download PDFInfo
- Publication number
- CN106782506A CN106782506A CN201611037945.6A CN201611037945A CN106782506A CN 106782506 A CN106782506 A CN 106782506A CN 201611037945 A CN201611037945 A CN 201611037945A CN 106782506 A CN106782506 A CN 106782506A
- Authority
- CN
- China
- Prior art keywords
- node
- pause
- recorded audio
- divided
- section
- 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 35
- 230000004069 differentiation Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 abstract description 7
- 230000015572 biosynthetic process Effects 0.000 abstract description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000006467 substitution reaction Methods 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
- G10L15/04—Segmentation; Word boundary detection
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing For Digital Recording And Reproducing (AREA)
- Management Or Editing Of Information On Record Carriers (AREA)
Abstract
Recorded audio is divided into the method for section the invention discloses a kind of, it is characterized in that comprising the following steps：Recorded audio data are obtained and traveled through, phonological component and mute part is obtained；At setting pause；Several nodes are formed according to time division, node serial number is set；Section is formed between two adjacent nodes；Node is modified；It is described to be whether decision node belongs at pause to the method that node is modified, if node is not belonging at pause, then at the supreme pause of knot adjustment；If node belongs at pause, continue to correct next node until terminating；The time of the mute part is the time difference between two adjacent phonological components.Advantage is:1. the audio segmentation of Large Copacity facilitates storage to take into some sections；2. the node for splitting formation during segmentation belongs at pause（Usually sentence tail or section tail）, it is to avoid audio loss, enhance Consumer's Experience.
Description
Technical field
The invention belongs to the present invention relates to field of audio processing, more particularly to a kind of side that recorded audio is divided into section
Method.
Background technology
With continuing to develop for Internet technology, the multi-medium data such as image, video, audio has been increasingly becoming internet letter
Main information medium form in breath process field.Wherein, voice data occupies critically important position.Original audio data is in itself
It is that a kind of non-semantic symbol is represented and non-structured binary stream.Often capacity is very for the recorded audio formed in convention
Greatly, the time is very long, and person for recording has many people, and that user needs is often wherein a bit of, or someone audio,
The audio segmentation Large Copacity is at this time accomplished by into some sections, facilitates storage to take, shape is often split during segmentation
Into node at be not a tail or section tail（It is defined as at pause）, audio loss can be caused, while also resulting in user's body
Test bad.
The content of the invention
The technical problems to be solved by the invention be audio segmentation formed node at be not so as to cause audio at pause
Loss and the bad problem of Consumer's Experience, and the method for improving this problem will be exactly adjusted to pause at spliting node.
In order to solve the above technical problems, the invention provides a kind of method that recorded audio is divided into section, it is characterized in that
Comprise the following steps：
Recorded audio data are obtained and traveled through, phonological component and mute part is obtained；
At setting pause；
Several nodes are formed according to time division, node serial number is set；
Section is formed between two adjacent nodes；
Node is modified；
It is described to be whether decision node belongs at pause to the method that node is modified, if node is not belonging at pause, that
At the supreme pause of knot adjustment；
If node belongs at pause, continue to correct next node until terminating；
The time of the mute part is the time difference between two adjacent phonological components.
Further, the method at the setting pause is that the average mute time of the Time Calculation according to mute part will be big
It is judged as at pause in the mute part of the threshold value of average mute time.
Further, the step of Time Calculation according to mute part average mute time is to obtain mute part
Total duration, and mute part quantity, calculated divided by the quantity of mute part with the total duration of mute part average Jing Yin
Time.
Further, the method at the setting pause is the median of the time for taking mute part and is set as at pause.
Further, the method at the setting pause is to record the sample of recorded audio according to custom word speed by person for recording,
The sample of the recorded audio is including at a pause, will be set as the pause of recorded audio at the pause of the sample of recorded audio
Place.
Further, it is described amendment node method also include node before and/or node after character whether with node label
Tag match in storehouse, the node label storehouse be store some sentences section start or word label that section terminates language material
Storehouse.
Further, whether the method also character including decision node of the amendment node changes tag match with personage,
It is to be used to the personage's differentiation identifier distinguished according to what the sound of people was differently formed in recording that the personage changes label.
Using above-mentioned technical proposal, following effect is can reach：
1. the audio segmentation of Large Copacity facilitates storage to take into some sections；
2. the node for splitting formation during segmentation belongs at pause（Usually sentence tail or section tail）, it is to avoid audio damage
Lose, enhance Consumer's Experience.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this hair
Bright schematic description and description does not constitute inappropriate limitation of the present invention, in the accompanying drawings for explaining the present invention：
Fig. 1 shows a kind of schematic flow sheet of the method that recorded audio is divided into section.
Specific embodiment
Technical scheme is further described in detail with reference to the accompanying drawings and detailed description.
In order to solve the above technical problems, as shown in figure 1, the invention provides a kind of side that recorded audio is divided into section
Method, it is characterized in that comprising the following steps：
Recorded audio data are obtained and traveled through, phonological component and mute part is obtained；
At setting pause；
Several nodes are formed according to time division, node serial number is set；
Section is formed between two adjacent nodes；
Node is modified；
It is described to be whether decision node belongs at pause to the method that node is modified, if node is not belonging at pause, that
At the supreme pause of knot adjustment；
If node belongs at pause, continue to correct next node until all node processings are terminated；
The time of the mute part is the time difference between two adjacent phonological components.
Further, the method at the setting pause is that the average mute time of the Time Calculation according to mute part will be big
It is judged as at pause in the mute part of the threshold value of average mute time.
Further, the step of Time Calculation according to mute part average mute time is to obtain mute part
Total duration, and mute part quantity, calculated divided by the quantity of mute part with the total duration of mute part average Jing Yin
Time.
Further, the method at the setting pause is the median of the time for taking mute part and is set as at pause.
Further, the method at the setting pause is to record the sample of recorded audio according to custom word speed by person for recording,
The sample of the recorded audio is including at a pause, will be set as the pause of recorded audio at the pause of the sample of recorded audio
Place.
Further, it is described amendment node method also include node before and/or node after character whether with node label
Tag match in storehouse, the node label storehouse be store some sentences section start or word label that section terminates language material
Storehouse.
Further, whether the method also character including decision node of the amendment node changes tag match with personage,
It is to be used to the personage's differentiation identifier distinguished according to what the sound of people was differently formed in recording that the personage changes label.
It should also be appreciated by one skilled in the art that the foregoing is only the preferred embodiments of the present invention, it is not used to
The limitation present invention, for a person skilled in the art, the present invention can have various modifications and variations.It is all in essence of the invention
Within god and principle, any modification, equivalent substitution and improvements made etc. should be included within the scope of the present invention.
Claims (7)
1. it is a kind of that recorded audio is divided into the method for section, it is characterized in that comprising the following steps：
Recorded audio data are obtained and traveled through, phonological component and mute part is obtained；
At setting pause；
Several nodes are formed according to time division, node serial number is set；
Section is formed between two adjacent nodes；
Node is modified；
It is described to be whether decision node belongs at pause to the method that node is modified, if node is not belonging at pause, that
At the supreme pause of knot adjustment；
If node belongs at pause, continue to correct next node until terminating；
The time of the mute part is the time difference between two adjacent phonological components.
2. the method that recorded audio is divided into section according to claim 1, it is characterized in that the side at the setting pause
Method is that the average mute time of the Time Calculation according to mute part, the mute part that will be greater than the threshold value of average mute time is sentenced
Break as at pause.
3. the method that recorded audio is divided into section according to claim 2, it is characterized in that described according to mute part
The step of Time Calculation average mute time is the quantity for obtaining the total duration of mute part, and mute part, uses Jing Yin portion
The total duration divided calculates average mute time divided by the quantity of mute part.
4. the method that recorded audio is divided into section according to claim 1, it is characterized in that the side at the setting pause
Method is the median of the time for taking mute part and is set as at pause.
5. the method that recorded audio is divided into section according to claim 1, it is characterized in that the side at the setting pause
Method is to record the sample of recorded audio according to custom word speed by person for recording, and the sample of the recorded audio is included at a pause,
To be set as at the pause of recorded audio at the pause of the sample of recorded audio.
6. the method that recorded audio is divided into section according to claim 1, it is characterized in that the method for the amendment node
Also include node before and/or node after character whether with node label storehouse in tag match, the node label storehouse is to deposit
Stored up some sentences section start or word label that section terminates corpus.
7. the method that recorded audio is divided into section according to claim 1, it is characterized in that the method for the amendment node
Also whether the character including decision node changes tag match with personage, and it is according to people in recording that the personage changes label
What sound was differently formed is used to the personage's differentiation identifier distinguished.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611037945.6A CN106782506A (en) | 2016-11-23 | 2016-11-23 | A kind of method that recorded audio is divided into section |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611037945.6A CN106782506A (en) | 2016-11-23 | 2016-11-23 | A kind of method that recorded audio is divided into section |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106782506A true CN106782506A (en) | 2017-05-31 |
Family
ID=58975016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611037945.6A Pending CN106782506A (en) | 2016-11-23 | 2016-11-23 | A kind of method that recorded audio is divided into section |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106782506A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108172219A (en) * | 2017-11-14 | 2018-06-15 | 珠海格力电器股份有限公司 | The method and apparatus for identifying voice |
| CN108962283A (en) * | 2018-01-29 | 2018-12-07 | 北京猎户星空科技有限公司 | A kind of question terminates the determination method, apparatus and electronic equipment of mute time |
| CN109166570A (en) * | 2018-07-24 | 2019-01-08 | 百度在线网络技术（北京）有限公司 | A kind of method, apparatus of phonetic segmentation, equipment and computer storage medium |
| CN109389999A (en) * | 2018-09-28 | 2019-02-26 | 北京亿幕信息技术有限公司 | A kind of high performance audio-video is made pauses in reading unpunctuated ancient writings method and system automatically |
| CN109448455A (en) * | 2018-12-20 | 2019-03-08 | 广东小天才科技有限公司 | A kind of real-time error recites method and private tutor's equipment |
| CN110473519A (en) * | 2018-05-11 | 2019-11-19 | 北京国双科技有限公司 | A kind of method of speech processing and device |
| CN112256871A (en) * | 2020-10-16 | 2021-01-22 | 国网江苏省电力有限公司连云港供电分公司 | Material fulfillment system and method |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1624685A (en) * | 2003-12-02 | 2005-06-08 | 英业达股份有限公司 | Paragraph type language learning system and its method |
| CN1716380A (en) * | 2005-07-26 | 2006-01-04 | 浙江大学 | Audio frequency splitting method for changing detection based on decision tree and speaking person |
| CN101221762A (en) * | 2007-12-06 | 2008-07-16 | 上海大学 | MP3 compression field audio partitioning method |
| CN101749951A (en) * | 2008-12-17 | 2010-06-23 | 上海立谊环保工程技术有限公司 | Treatment method for segmentation of metallurgy sintering smoke |
| CN102591892A (en) * | 2011-01-13 | 2012-07-18 | 索尼公司 | Data segmenting device and method |
| CN103247317A (en) * | 2013-04-03 | 2013-08-14 | 深圳大学 | Editing method and system for record files |
| CN102348049B (en) * | 2011-09-16 | 2013-09-18 | 央视国际网络有限公司 | Method and device for detecting position of cut point of video segment |
| CN103646654A (en) * | 2013-12-12 | 2014-03-19 | 深圳市金立通信设备有限公司 | Recording data sharing method and terminal |
| CN103812754A (en) * | 2012-11-12 | 2014-05-21 | 腾讯科技（深圳）有限公司 | Contact matching method, instant messaging client, server and system |
| CN104519401A (en) * | 2013-09-30 | 2015-04-15 | 华为技术有限公司 | Video division point acquiring method and equipment |
| CN105336321A (en) * | 2015-09-25 | 2016-02-17 | 百度在线网络技术（北京）有限公司 | Phonetic segmentation method and device for speech synthesis |
| CN105653729A (en) * | 2016-01-28 | 2016-06-08 | 努比亚技术有限公司 | Device and method for indexing sound recording file |
| CN105719642A (en) * | 2016-02-29 | 2016-06-29 | 黄博 | Continuous and long voice recognition method and system and hardware equipment |
| WO2016112519A1 (en) * | 2015-01-15 | 2016-07-21 | 华为技术有限公司 | Audio content segmentation method and apparatus |
| 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 |
-
2016
- 2016-11-23 CN CN201611037945.6A patent/CN106782506A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1624685A (en) * | 2003-12-02 | 2005-06-08 | 英业达股份有限公司 | Paragraph type language learning system and its method |
| CN1716380A (en) * | 2005-07-26 | 2006-01-04 | 浙江大学 | Audio frequency splitting method for changing detection based on decision tree and speaking person |
| CN101221762A (en) * | 2007-12-06 | 2008-07-16 | 上海大学 | MP3 compression field audio partitioning method |
| CN101749951A (en) * | 2008-12-17 | 2010-06-23 | 上海立谊环保工程技术有限公司 | Treatment method for segmentation of metallurgy sintering smoke |
| CN102591892A (en) * | 2011-01-13 | 2012-07-18 | 索尼公司 | Data segmenting device and method |
| CN102348049B (en) * | 2011-09-16 | 2013-09-18 | 央视国际网络有限公司 | Method and device for detecting position of cut point of video segment |
| CN103812754A (en) * | 2012-11-12 | 2014-05-21 | 腾讯科技（深圳）有限公司 | Contact matching method, instant messaging client, server and system |
| CN103247317A (en) * | 2013-04-03 | 2013-08-14 | 深圳大学 | Editing method and system for record files |
| CN104519401A (en) * | 2013-09-30 | 2015-04-15 | 华为技术有限公司 | Video division point acquiring method and equipment |
| CN103646654A (en) * | 2013-12-12 | 2014-03-19 | 深圳市金立通信设备有限公司 | Recording data sharing method and terminal |
| WO2016112519A1 (en) * | 2015-01-15 | 2016-07-21 | 华为技术有限公司 | Audio content segmentation method and apparatus |
| CN105336321A (en) * | 2015-09-25 | 2016-02-17 | 百度在线网络技术（北京）有限公司 | Phonetic segmentation method and device for speech synthesis |
| CN105653729A (en) * | 2016-01-28 | 2016-06-08 | 努比亚技术有限公司 | Device and method for indexing sound recording file |
| CN105719642A (en) * | 2016-02-29 | 2016-06-29 | 黄博 | Continuous and long voice recognition method and system and hardware equipment |
| 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 |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108172219A (en) * | 2017-11-14 | 2018-06-15 | 珠海格力电器股份有限公司 | The method and apparatus for identifying voice |
| CN108962283A (en) * | 2018-01-29 | 2018-12-07 | 北京猎户星空科技有限公司 | A kind of question terminates the determination method, apparatus and electronic equipment of mute time |
| CN110473519A (en) * | 2018-05-11 | 2019-11-19 | 北京国双科技有限公司 | A kind of method of speech processing and device |
| CN110473519B (en) * | 2018-05-11 | 2022-05-27 | 北京国双科技有限公司 | Voice processing method and device |
| CN109166570A (en) * | 2018-07-24 | 2019-01-08 | 百度在线网络技术（北京）有限公司 | A kind of method, apparatus of phonetic segmentation, equipment and computer storage medium |
| CN109389999A (en) * | 2018-09-28 | 2019-02-26 | 北京亿幕信息技术有限公司 | A kind of high performance audio-video is made pauses in reading unpunctuated ancient writings method and system automatically |
| CN109389999B (en) * | 2018-09-28 | 2020-12-11 | 北京亿幕信息技术有限公司 | High-performance audio and video automatic sentence-breaking method and system |
| CN109448455A (en) * | 2018-12-20 | 2019-03-08 | 广东小天才科技有限公司 | A kind of real-time error recites method and private tutor's equipment |
| CN112256871A (en) * | 2020-10-16 | 2021-01-22 | 国网江苏省电力有限公司连云港供电分公司 | Material fulfillment system and method |
| CN112256871B (en) * | 2020-10-16 | 2021-05-07 | 国网江苏省电力有限公司连云港供电分公司 | Material fulfillment system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106782506A (en) | A kind of method that recorded audio is divided into section | |
| CN107195295B (en) | Voice recognition method and device based on Chinese-English mixed dictionary | |
| CN109065033B (en) | Automatic speech recognition method based on random deep time delay neural network model | |
| KR102598824B1 (en) | Automated voice translation dubbing for prerecorded videos | |
| CN108829894B (en) | Spoken word recognition and semantic recognition method and device | |
| WO2018036555A1 (en) | Session processing method and apparatus | |
| WO2020087655A1 (en) | Translation method, apparatus and device, and readable storage medium | |
| CN108630193A (en) | Audio recognition method and device | |
| CN105208463B (en) | The method and system of frame determination is carried out for m3u8 files | |
| CN110085261A (en) | A kind of pronunciation correction method, apparatus, equipment and computer readable storage medium | |
| US10984801B2 (en) | ASR training and adaptation | |
| JP2004229283A (en) | Method for identifying transition of news presenter in news video | |
| CN112992125B (en) | Voice recognition method and device, electronic equipment and readable storage medium | |
| CN110706695B (en) | Data labeling method and device | |
| CN112541095B (en) | Video title generation method and device, electronic equipment and storage medium | |
| CN111627423B (en) | VAD tail point detection method, device, server and computer readable medium | |
| CN107517406A (en) | A kind of video clipping and the method for translation | |
| CN108549628A (en) | The punctuate device and method of streaming natural language information | |
| CN112016271A (en) | Language style conversion model training method, text processing method and device | |
| CN107181986A (en) | The matching process and device of video and captions | |
| WO2023151424A1 (en) | Method and apparatus for adjusting playback rate of audio picture of video | |
| CN112800263A (en) | Video synthesis system, method and medium based on artificial intelligence | |
| Alluri et al. | Multi Modal Analysis of memes for Sentiment extraction | |
| KR101389730B1 (en) | Method to create split position accordance with subjects for the video file | |
| US20100278505A1 (en) | Multi-media data editing system, method and electronic device using same |
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: 20170531 |