CN106128460A - A kind of record labels method and device - Google Patents
A kind of record labels method and device Download PDFInfo
- Publication number
- CN106128460A CN106128460A CN201610635354.2A CN201610635354A CN106128460A CN 106128460 A CN106128460 A CN 106128460A CN 201610635354 A CN201610635354 A CN 201610635354A CN 106128460 A CN106128460 A CN 106128460A
- Authority
- CN
- China
- Prior art keywords
- key sentence
- record labels
- time point
- recording
- key
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
- G11B27/10—Indexing; Addressing; Timing or synchronising; Measuring tape travel
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/64—Automatic arrangements for answering calls; Automatic arrangements for recording messages for absent subscribers; Arrangements for recording conversations
- H04M1/65—Recording arrangements for recording a message from the calling party
- H04M1/6505—Recording arrangements for recording a message from the calling party storing speech in digital form
Abstract
The present invention is applicable to record labels field, it is provided that a kind of record labels method and device, described record labels method includes: during recording, the key sentence set by speech recognition system identification;The time point of the key sentence recognized with the key sentence place recognized is saved in data base or recording file.It is that simple recording can not be added labelling or manually can only add labelling for regular time point that the present invention solves existing recording technology great majority, record labels is the most entirely and the longest, the problem being unfavorable for improving the efficiency of record labels, have the beneficial effects that following two aspects, on the one hand, by the key sentence in recording is identified automatically, substantially increase the efficiency of later stage process recording;On the other hand, different key sentence can be set so that record labels is complete and the shortest according to different demands, be conducive to improving efficiency and the degree of intelligence of record labels.
Description
Technical field
The invention belongs to record labels field, particularly relate to a kind of record labels method and device.
Background technology
Recording technology is widely used in digital equipment, and the digital equipment such as mobile phone, MP3, MP4, DV is respectively provided with
Recorder function.User's sound-recording function by digital equipment, can carry out record to thing at one's side, in order to more whenever and wherever possible
Clearly recovery record is on-the-spot.
But, existing recording technology great majority are that simple recording can not add labelling or can only be manually for solid
Fixed time point adds labelling, and record labels the most entirely and the longest, is unfavorable for improving the efficiency of record labels.Its reason is,
Existing recording technology is the most perfect in the process to recording data, especially finds spy when wanting in one section of recording the longest
Need during fixed statement to listen from the beginning to the end one time very inconvenient, specific statement added time labelling the most very may be used even if manual
Some places can be missed and there is no labelling.Therefore, record labels the most entirely and the longest, can not meet the digital equipment labelling to recording
Demand.
Summary of the invention
The purpose of the embodiment of the present invention is to provide a kind of record labels method, it is intended to solve existing recording technology most
The recording that number is the most simple can not be added labelling or manually can only add labelling for regular time point, and record labels is the most complete
And the longest, it is unfavorable for improving the problem of efficiency of record labels.
The embodiment of the present invention is achieved in that a kind of record labels method, including:
During recording, the key sentence set by speech recognition system identification;
The time point of the key sentence recognized with the key sentence place recognized is saved in data base or recording
In file.
The another object of the embodiment of the present invention is to provide a kind of record labels device, including:
Key sentence identification module, when being used for recording, the key sentence set by speech recognition system identification;
Key sentence preserves module, is preserved by the time point of the key sentence recognized with the key sentence place recognized
In data base or recording file.
In embodiments of the present invention, the time point of the key sentence recognized with the key sentence place recognized is preserved
In data base or recording file, solve existing recording technology great majority be simple recording can not add labelling or
Person manually can only add labelling for regular time point, and record labels the most entirely and the longest, is unfavorable for improving record labels
The problem of efficiency.Having the beneficial effects that following two aspects, details are as follows:
On the one hand, by the key sentence in recording is identified automatically, substantially increase the effect of later stage process recording
Rate;
On the other hand, different key sentence can be set so that record labels is complete and the shortest according to different demands,
Be conducive to improving efficiency and the degree of intelligence of record labels.
Accompanying drawing explanation
Fig. 1 is the flowchart of the record labels method that the embodiment of the present invention provides;
Fig. 2 is the flowchart of the record labels method step S103 that the embodiment of the present invention provides;
Fig. 3 is the flowchart of the key sentence playing function that the embodiment of the present invention provides;
Fig. 4 is the structured flowchart of the record labels device that the embodiment of the present invention provides.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, right
The present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, and
It is not used in the restriction present invention.
Embodiment one
Fig. 1 is the flowchart of the record labels method that the embodiment of the present invention provides, and details are as follows:
In step S101, during recording, the key sentence set by speech recognition system identification;
In the data channel of recording, embed the speech recognition program of speech recognition system;
Utilize the speech recognition program embedded, voice data identifies the key sentence of setting.
Before step S101, described record labels method, including:
Setting key sentence, described key sentence includes one or a combination set of key word and critical sentence.
Receive the word of input;
The word received is set as key word.
Receive the sentence of input;
The sentence received is set as critical sentence.
In step s 102, the time point of the key sentence recognized with the key sentence place recognized is saved in number
According in storehouse or recording file.
The network schemer using described setting uploads recording file to recording server, to complete the backup of recording file,
The network schemer of described setting includes WIFI network pattern, 2G network schemer, 3G network pattern, 4G network schemer, 5G network mould
At least one in formula.
In embodiments of the present invention, recording and labelling key sentence synchronize to carry out, and solve existing recording technology most
The recording that number is the most simple can not be added labelling or manually can only add labelling for regular time point, and record labels is the most complete
And the longest, it is unfavorable for improving the problem of efficiency of record labels.Having the beneficial effects that following two aspects, details are as follows:
On the one hand, by the key sentence in recording is identified automatically, substantially increase the effect of later stage process recording
Rate, can skip tediously long opening speech and jump directly to, as marked " beginning ", the place formally started of recording, it is not necessary to drag progress
Bar finds " beginning " key word, and this point is especially effective in one section of very long recording;
On the other hand, can set different key sentence according to different demands, the multiple key sentence of labelling then allows recording
Clear in structure, it is easy to extract the recording substance that goes for so that record labels is complete and the shortest, be conducive to improving recording mark
The efficiency of note and degree of intelligence.
Embodiment two
What the embodiment of the present invention described record labels method step S102 realizes flow process, and details are as follows:
During recording, the same key sentence occurred by the multiple time point of speech recognition system identification.
During recording, whether repeated by speech recognition system detection key sentence, when key sentence repeats,
The key sentence repeated is identified as the same key sentence that multiple time point occurs.
Embodiment three
Fig. 2 is the flowchart of the record labels method step S103 that the embodiment of the present invention provides, and details are as follows:
In step s 201, described key sentence is set up with the time point at the key sentence place recognized and associates, structure
Become record labels data structure;
Wherein, the key word recognized is set up with multiple time points at same key word place and associates, constitute recording
Flag data structure;Or,
The critical sentence recognized is set up with multiple time points at same critical sentence place and associates, constitute record labels number
According to structure.
When described key sentence is associated with the time point foundation at the key sentence place recognized, if only recognizing one
Individual time point, described key sentence is one to one with the corresponding relation of the time point at the key sentence place recognized.If knowing
Being clipped to multiple time point, described key sentence is one-to-many with the corresponding relation of the time point at the key sentence place recognized.
Other embodiments has multiple time point to be also to fix one to one, and detailed description of the invention does not limits at this.
In step S202, record labels data structure is saved in data base or recording file.Wherein, for ease of
Illustrate, to arrange key sentence for as a example by " beginning " and " end ".
The time " starting " to occur, " end " occurred in 55:20 at 1:30 and 40:15.
When as 1:30, speech recognition system identifies " beginning ", advising process starts to preserve this time to " beginning " correspondence
Entry.
Be carried out same steps during 40:15 and 55:20, the record labels data structure finally preserved approximately as:
Beginning-1:30-40:15;
End-55:20.
It is one to one with corresponding relation, arranges as a example by key sentence is A and B.
The time that A occurs occurs in 55:20 at 3:30, B.
By the time point 3:30 of A with the key sentence place recognized, set up association, constitute record labels data structure.
By the time point 55:20 of B with the key sentence place recognized, set up association, constitute record labels data structure.
It is one-to-many with corresponding relation, arranges as a example by key sentence is A and B.
The time that A occurs occurs in 21:20,55:20 at 3:30,7:30, B.
By time point 3:30,7:30 of A with the key sentence place recognized, set up association, constitute record labels data
Structure.
By time point 21:20,55:20 of B with the key sentence place recognized, set up association, constitute record labels number
According to structure.
Embodiment four
What the embodiment of the present invention described record labels method step S102 realizes flow process, and details are as follows:
The time point of described key sentence and multiple key sentence place recognized is set up association in chronological order.
Wherein, for purposes of illustration only, to arrange key sentence for as a example by " beginning " and " end ".
The time " starting " to occur, " end " occurred in 55:20 at 1:30,9:20,23:27 and 40:15.
In chronological sequence order sets up association, and when as 1:30, speech recognition system identifies " beginning ", advising process is opened
Begin the entry preserving 1:30 to " beginning " correspondence, and when as 9:20, speech recognition system identifies " beginning ", advising process starts
Preserving the 9:20 entry to " beginning " correspondence, when as 23:27, speech recognition system identifies " beginning ", advising process starts to protect
Deposit the 23:27 entry to " beginning " correspondence.
Other embodiments can use and sort otherwise, such as first high for key sentence frequency of occurrence several
Before row etc..
Embodiment five
Fig. 3 is the flowchart of the key sentence playing function that the embodiment of the present invention provides, and details are as follows:
In step S301, showing key sentence list, described key sentence list includes key sentence and Key Words
The time point of sentence association;
Wherein, described key sentence includes one or a combination set of key word and critical sentence.
In step s 302, key sentence clicked in key sentence list is obtained;
In step S303, using the time point of clicked key sentence association as playing starting point, playing starting point,
Recording data in played data storehouse or recording file.
Wherein, the time point clicked key word or critical sentence associated, as playing starting point, is being play starting point, is being broadcast
Put the recording data in data base or recording file.
Embodiment six
What the embodiment of the present invention described marker color function realizes flow process, and details are as follows:
Use the color preset, the key sentence that marker recognition arrives;Or,
Use the color preset, the time point at the key sentence place that marker recognition arrives;Or,
Use the color preset, the progress bar between the time point at the key sentence place that labelling any two recognizes.
Wherein, the different colours preset, the different key sentence that marker recognition arrives are used.
Wherein, the different colours preset, the different time points at the key sentence place that marker recognition arrives are used.
Wherein, the progress bar between any two time point is set to the color different from common progress bar, as by
Progress bar between time point and the time point of " end " of two " beginnings " is labeled as blueness, by drag progress bar start from
Corresponding time point is play.
Embodiment seven
Fig. 4 is the structured flowchart of the record labels device that the embodiment of the present invention provides, and this device can run on electronics and set
In Bei.For convenience of description, illustrate only part related to the present embodiment.
Reference Fig. 4, this record labels device, including:
Key sentence identification module 41, when being used for recording, the key sentence set by speech recognition system identification;
Key sentence preserves module 42, is protected by the time point of the key sentence recognized with the key sentence place recognized
It is stored in data base or recording file.
As a kind of implementation of the present embodiment, in described record labels device, described key sentence preserves module,
Including:
Associative cell, associates for described key sentence being set up with the time point at the key sentence place recognized, structure
Become record labels data structure;
Key sentence storage unit, is saved in record labels data structure in data base or recording file.
As a kind of implementation of the present embodiment, described record labels device, also include:
Display module, is used for showing that key sentence list, described key sentence list include key sentence and Key Words
The time point of sentence association;
Acquisition module, for obtaining key sentence clicked in key sentence list;
Playing module, is used for the time point of clicked key sentence association as playing starting point, is playing starting point,
Recording data in played data storehouse or recording file.
As a kind of implementation of the present embodiment, described record labels device, also include:
Marker color functional module, for using default color, the key sentence that marker recognition arrives;Or,
Use the color preset, the time point at the key sentence place that marker recognition arrives;Or,
Use the color preset, the progress bar between the time point at the key sentence place that labelling any two recognizes.
As a kind of implementation of the present embodiment, in described record labels device, described key sentence identification module
During specifically for recording, the same key sentence occurred by the multiple time point of speech recognition system identification.
The device that the embodiment of the present invention provides can be applied in the embodiment of the method for aforementioned correspondence, and details see above-mentioned reality
Execute the description of example, do not repeat them here.
Through the above description of the embodiments, those skilled in the art is it can be understood that can borrow to the present invention
The mode helping software to add required common hardware realizes.Described program can be stored in read/write memory medium, described
Storage medium, as random access memory, flash memory, read only memory, programmable read only memory, electrically erasable programmable storage
Device, depositor etc..This storage medium is positioned at memorizer, and processor reads the information in memorizer, performs this in conjunction with its hardware
Method described in each embodiment bright.
The above, the only detailed description of the invention of the present invention, but protection scope of the present invention is not limited thereto, and any
Those familiar with the art in the technical scope that the invention discloses, the change that can readily occur in or replacement, all answer
Contain within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with scope of the claims.
Claims (10)
1. a record labels method, it is characterised in that including:
During recording, the key sentence set by speech recognition system identification;
The time point of described key sentence with the key sentence place recognized is saved in data base or recording file.
2. record labels method as claimed in claim 1, it is characterised in that described by the key sentence recognized with recognize
The time point at key sentence place be saved in data base or recording file, particularly as follows:
Described key sentence is set up with the time point at the key sentence place recognized and associates, constitute record labels data knot
Structure;
Record labels data structure is saved in data base or recording file.
3. record labels method as claimed in claim 2, it is characterised in that described by described key sentence with the pass that recognizes
The time point at key statement place sets up association, particularly as follows:
The time point of described key sentence and multiple key sentence place recognized is set up association in chronological order.
4. record labels method as claimed in claim 1, it is characterised in that described record labels method, also includes:
Display key sentence list, described key sentence list includes the time point that key sentence associates with key sentence;
Obtain key sentence clicked in key sentence list;
Using the time point of clicked key sentence association as playing starting point, playing starting point, played data storehouse or record
Recording data in sound file.
5. record labels method as claimed in claim 1, it is characterised in that described record labels method, also includes:
Use the color preset, the key sentence that marker recognition arrives;Or,
Use the color preset, the time point at the key sentence place that marker recognition arrives;Or,
Use the color preset, the progress bar between the time point at the key sentence place that labelling any two recognizes.
6. a record labels device, it is characterised in that including:
Key sentence identification module, when being used for recording, the key sentence set by speech recognition system identification;
Key sentence preserves module, and the time point of the key sentence recognized with the key sentence place recognized is saved in number
According in storehouse or recording file.
7. record labels device as claimed in claim 6, it is characterised in that described key sentence preserves module, including:
Associative cell, associates for described key sentence being set up with the time point at the key sentence place recognized, constitutes record
Sound flag data structure;
Key sentence storage unit, is saved in record labels data structure in data base or recording file.
8. record labels device as claimed in claim 7, it is characterised in that described associative cell is specifically for by described key
The time point at statement and multiple key sentence place recognized sets up association in chronological order.
9. record labels device as claimed in claim 6, it is characterised in that described record labels device, also includes:
Display module, is used for showing that key sentence list, described key sentence list include that key sentence and key sentence are closed
The time point of connection;
Acquisition module, for obtaining key sentence clicked in key sentence list;
Playing module, is used for the time point of clicked key sentence association as playing starting point, is playing starting point, playing
Recording data in data base or recording file.
10. record labels device as claimed in claim 6, it is characterised in that described record labels device, also includes:
Marker color functional module, for using default color, the key sentence that marker recognition arrives;Or,
Use the color preset, the time point at the key sentence place that marker recognition arrives;Or,
Use the color preset, the progress bar between the time point at the key sentence place that labelling any two recognizes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610635354.2A CN106128460A (en) | 2016-08-04 | 2016-08-04 | A kind of record labels method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610635354.2A CN106128460A (en) | 2016-08-04 | 2016-08-04 | A kind of record labels method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106128460A true CN106128460A (en) | 2016-11-16 |
Family
ID=57255805
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610635354.2A Pending CN106128460A (en) | 2016-08-04 | 2016-08-04 | A kind of record labels method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106128460A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107610718A (en) * | 2017-08-29 | 2018-01-19 | 深圳市买买提乐购金融服务有限公司 | A kind of method and device that voice document content is marked |
CN109165923A (en) * | 2018-08-24 | 2019-01-08 | 民航中南空管设备工程公司 | project management system |
WO2019205119A1 (en) * | 2018-04-28 | 2019-10-31 | 海能达通信股份有限公司 | Voice playback method and device, and client |
CN110719518A (en) * | 2018-07-12 | 2020-01-21 | 阿里巴巴集团控股有限公司 | Multimedia data processing method, device and equipment |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0780777A1 (en) * | 1995-12-21 | 1997-06-25 | Hewlett-Packard Company | Indexing of recordings |
JP2009044466A (en) * | 2007-08-09 | 2009-02-26 | Hitachi Ltd | Apparatus for automatically video-recording recommended program |
CN102483917A (en) * | 2009-07-15 | 2012-05-30 | 谷歌公司 | Commands directed at displayed text |
US20130055334A1 (en) * | 2011-08-31 | 2013-02-28 | Yutaka Ueda | Video processor, television display device, and video processing method |
CN103345931A (en) * | 2013-06-20 | 2013-10-09 | 张家港保税区润桐电子技术研发有限公司 | Music playing method |
CN104078044A (en) * | 2014-07-02 | 2014-10-01 | 深圳市中兴移动通信有限公司 | Mobile terminal and sound recording search method and device of mobile terminal |
CN104184870A (en) * | 2014-07-29 | 2014-12-03 | 小米科技有限责任公司 | Call log marking method and device and electronic equipment |
CN104599692A (en) * | 2014-12-16 | 2015-05-06 | 上海合合信息科技发展有限公司 | Recording method and device and recording content searching method and device |
CN104766604A (en) * | 2015-04-02 | 2015-07-08 | 努比亚技术有限公司 | Voice data marking method and device |
CN105702278A (en) * | 2016-04-19 | 2016-06-22 | 珠海格力电器股份有限公司 | Method, device and terminal for recording sound of conferences |
-
2016
- 2016-08-04 CN CN201610635354.2A patent/CN106128460A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0780777A1 (en) * | 1995-12-21 | 1997-06-25 | Hewlett-Packard Company | Indexing of recordings |
JP2009044466A (en) * | 2007-08-09 | 2009-02-26 | Hitachi Ltd | Apparatus for automatically video-recording recommended program |
CN102483917A (en) * | 2009-07-15 | 2012-05-30 | 谷歌公司 | Commands directed at displayed text |
US20130055334A1 (en) * | 2011-08-31 | 2013-02-28 | Yutaka Ueda | Video processor, television display device, and video processing method |
CN103345931A (en) * | 2013-06-20 | 2013-10-09 | 张家港保税区润桐电子技术研发有限公司 | Music playing method |
CN104078044A (en) * | 2014-07-02 | 2014-10-01 | 深圳市中兴移动通信有限公司 | Mobile terminal and sound recording search method and device of mobile terminal |
CN104184870A (en) * | 2014-07-29 | 2014-12-03 | 小米科技有限责任公司 | Call log marking method and device and electronic equipment |
CN104599692A (en) * | 2014-12-16 | 2015-05-06 | 上海合合信息科技发展有限公司 | Recording method and device and recording content searching method and device |
CN104766604A (en) * | 2015-04-02 | 2015-07-08 | 努比亚技术有限公司 | Voice data marking method and device |
CN105702278A (en) * | 2016-04-19 | 2016-06-22 | 珠海格力电器股份有限公司 | Method, device and terminal for recording sound of conferences |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107610718A (en) * | 2017-08-29 | 2018-01-19 | 深圳市买买提乐购金融服务有限公司 | A kind of method and device that voice document content is marked |
WO2019205119A1 (en) * | 2018-04-28 | 2019-10-31 | 海能达通信股份有限公司 | Voice playback method and device, and client |
CN110719518A (en) * | 2018-07-12 | 2020-01-21 | 阿里巴巴集团控股有限公司 | Multimedia data processing method, device and equipment |
CN109165923A (en) * | 2018-08-24 | 2019-01-08 | 民航中南空管设备工程公司 | project management system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106128460A (en) | A kind of record labels method and device | |
US9113125B2 (en) | Techniques for indexing video files | |
CN102750962B (en) | A kind of back method of video file and device | |
CN106297843A (en) | A kind of record labels display packing and device | |
CN105975569A (en) | Voice processing method and terminal | |
CN104978145A (en) | Recording realization method and apparatus and mobile terminal | |
CN104599692A (en) | Recording method and device and recording content searching method and device | |
CN104239458A (en) | Method and device for representing search results | |
WO2016197708A1 (en) | Recording method and terminal | |
CN102385610B (en) | Digital hard disc video recorder video file is preserved method and the system thereof recovered with data | |
US20120035919A1 (en) | Voice recording device and method thereof | |
CN103871438A (en) | Message record and playback system and method thereof | |
US8868429B2 (en) | Method and device for storing audio data | |
CN103794233B (en) | A kind of storage means of video/audio and storage device | |
US20130262375A1 (en) | Method for managing electronic phone book used in communication devices | |
CN103984931A (en) | Information processing method and first electronic equipment | |
CN106528715A (en) | Method and device for checking audio content | |
US20140376885A1 (en) | Method for playing video file and electronic device using the same | |
CN107195314B (en) | The method for recording and device of audio data | |
US9609277B1 (en) | Playback system of video conference record and method for video conferencing record | |
US20170123753A1 (en) | Electronic device and method for playing back sound data | |
CN103577035A (en) | Application interface processing device and method for electronic equipment, and electronic system | |
CN102831073B (en) | Internal memory data processing method and system | |
CN103488433B (en) | A kind of batch documents method of operating and system based on distributed file system | |
CN103702046A (en) | Method for opening voice equipment in selectable mode |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161116 |
|
RJ01 | Rejection of invention patent application after publication |