CN107480159A - The input method and device of a kind of speech data - Google Patents
The input method and device of a kind of speech data Download PDFInfo
- Publication number
- CN107480159A CN107480159A CN201611100679.7A CN201611100679A CN107480159A CN 107480159 A CN107480159 A CN 107480159A CN 201611100679 A CN201611100679 A CN 201611100679A CN 107480159 A CN107480159 A CN 107480159A
- Authority
- CN
- China
- Prior art keywords
- data
- speech
- text
- text data
- database
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Abstract
The applicable field of computer technology of the present invention, there is provided the input method and device of a kind of speech data, methods described include：Text data and speech data corresponding with text data are formed into one-to-one relationship, and establish text database and speech database respectively；The text data of speech data to be logged is obtained, the text data of speech data to be logged is matched with the text data in text database；According to the text data matched, from speech data corresponding to speech database extraction.Text data and speech data are formed one-to-one relation by the present invention, by matched text data, realize existing same voice data in extraction speech database, avoid repeated taping, speech data is reused, reduces recording demand, so as to reduce cost.
Description
Technical field
The invention belongs to the input method and device of field of computer technology, more particularly to a kind of speech data.
Background technology
Papery resources material is made in teaching material, religion be auxiliary etc. for point reader or data source used in private tutor's machine at present, its
It is related to correspondingly obtaining speech data by the text data in resources material, so as to realize user in resources material is chosen
Corresponding speech data can be played out after text data, because resources material frequently refers to version updating, and simply more
New portion content, but generally require again to be recorded the text data in resources material, with voice number corresponding to acquisition
According to.So that existing voice data are underutilized, repeated taping undoubtedly increases time cost, so as to reduce efficiency.
The content of the invention
It is an object of the invention to provide a kind of input method of speech data and device, it is intended to solve in the prior art because
Resources material more redaction needs to be recorded again, the problem of causing existing speech data not reuse.
On the one hand, the invention provides a kind of input method of speech data, methods described to comprise the steps：
Text data and speech data corresponding with the text data are formed into one-to-one relationship, and established respectively
Text database and speech database；
The text data of speech data to be logged is obtained, by the text data of the speech data to be logged and the text
Text data in database is matched；
According to the text data matched, from speech data corresponding to speech database extraction.
On the other hand, the invention provides a kind of input device of speech data, described device to include：
Database unit, for text data and speech data corresponding with the text data to be formed one by one
Corresponding relation, and text database and speech database are established respectively；
Matching unit, for obtaining the text data of speech data to be logged, by the text of the speech data to be logged
Data are matched with the text data in the text database；And
Extraction unit, for according to the text data matched, from speech data corresponding to speech database extraction.
In embodiments of the present invention, text data and speech data are formed into one-to-one relation, passes through matched text
Data, existing same voice data in extraction speech database are realized, avoid repeated taping so that speech data can obtain
To recycling, reduce recording demand, so as to reduce cost.
Brief description of the drawings
Fig. 1 is the implementation process figure of the input method for the speech data that the embodiment of the present invention one provides；
Fig. 2 is the implementation process figure of the input method for the speech data that the embodiment of the present invention two provides；
Fig. 3 is the structural representation of the input device for the speech data that the embodiment of the present invention three provides；And
Fig. 4 is the structural representation of the input device for the speech data that the embodiment of the present invention four provides.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
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.
It is described in detail below in conjunction with specific implementation of the specific embodiment to the present invention：
Embodiment one：
Fig. 1 shows the implementation process figure of the input method for the speech data that the embodiment of the present invention one provides, for the ease of
Illustrate, illustrate only the part related to the embodiment of the present invention, details are as follows：
In step S101, text data and speech data corresponding with text data are formed into one-to-one relationship,
And text database and speech database are established respectively.
In embodiments of the present invention, private tutor's machine or point reader need to import the papery resources materials such as teaching material, tutorial,
Because resources material often updates revision, it is therefore desirable to which the resources material after renewal is imported.By integrating in the past
The teaching material of making teaches the text data of auxiliary book and speech data corresponding with text data, and text data and speech data are built
Vertical one-to-one relationship, and text database and speech database are formed, and persistence maintenance updates after there is newly revised edition sheet
Database.
Further, text data and speech data corresponding with text data are marked into same identification code.
Specifically, text data and speech data are established into one-to-one relationship, can be by text data and voice number
One-to-one relationship is realized according to mark identification code, is marked to a text data and with the speech data corresponding to this article notebook data
Same identification code, and the identification code is unique identification code, after to text data and speech data mark identification code, by text
Notebook data and speech data are stored in text database and speech database respectively.
In step s 102, the text data of speech data to be logged is obtained, by the text data of speech data to be logged
Matched with the text data in text database.
In embodiments of the present invention, when the resources material after having renewal needs to be imported, resources material is obtained first
Text data, the text data of speech data to be logged is matched with the text data in text database, to obtain
Identical text data, avoid carrying out repeated taping to text data so that speech data is efficiently utilized, will not be because of
There is the resources material after renewal just to give up original speech data.
Further, the character string of the text data of speech data to be logged is obtained；
The character string of the text data of speech data to be logged is matched character by character in text database.
Specifically, the character string of the text data of speech data to be logged is obtained, by the way that character string is carried out character by character
Match somebody with somebody, obtained in text database with the identical text data of the text data of speech data to be logged, effectively ensure
The accuracy of matching, while improve matching efficiency.
In step s 103, according to the text data matched, from speech data corresponding to speech database extraction.
In embodiments of the present invention, the text data in the text data and text database of speech data to be logged is entered
Row matching, after obtaining matching identical text data, from speech data corresponding to speech database extraction, avoid identical
The drawbacks of text data repeated taping, the importing time of new resources material is improved, efficiently utilize existing voice number
According to.
Further, the identification code of matched text data is obtained；
Extraction marks the speech data of same identification code in speech database.
Specifically, after identical text data is matched, the text data matched in text database is read only
One identification code, according to the identification code, the speech data for being marked with the identification code is extracted in speech database.
In embodiments of the present invention, text data and speech data are formed into one-to-one relation, passes through matched text
Data, existing same voice data in extraction speech database are realized, avoid repeated taping so that speech data can obtain
To recycling, reduce recording demand, so as to reduce cost.
Embodiment two：
Fig. 2 shows the implementation process figure of the input method for the speech data that the embodiment of the present invention two provides, for the ease of
Illustrate, illustrate only the part related to the embodiment of the present invention, details are as follows：
In step s 201, text data and speech data corresponding with text data are formed into one-to-one relationship,
And text database and speech database are established respectively.
In step S202, the text data of speech data to be logged is obtained, by the text data of speech data to be logged
Matched with the text data in text database.
In step S203, according to the text data matched, from speech data corresponding to speech database extraction.
In embodiments of the present invention, step S201-S203 embodiment can correspond to and refer to step in previous embodiment one
S101-S103 description, will not be repeated here.
In step S204, if being not matched to same text data in text database, by record obtain with
Speech data corresponding to text data.
In embodiments of the present invention, when being not matched to same text data in text database, then need to pass through
Speech data corresponding to recording acquisition.Specifically, can be by the way that text data be split, the character after being split, according to
Voice corresponding to secondary acquisition character, and these voices are combined to the speech data to form corresponding text data successively.
Can be with one of ordinary skill in the art will appreciate that realizing that all or part of step in above-described embodiment method is
The hardware of correlation is instructed to complete by program, described program can be stored in a computer read/write memory medium,
Described storage medium, such as ROM/RAM, disk, CD.
Embodiment three：
Fig. 3 shows the structural representation of the input device for the speech data that the embodiment of the present invention three provides, for the ease of
Illustrate, illustrate only the part related to the embodiment of the present invention.In embodiments of the present invention, the input device bag of speech data
Include：Database unit 31, matching unit 32 and extraction unit 33, wherein：
Database unit 31, for text data and speech data corresponding with text data to be formed one a pair
It should be related to, and establish text database and speech database respectively.
In embodiments of the present invention, private tutor's machine or point reader need to import the papery resources materials such as teaching material, tutorial,
Because resources material often updates revision, it is therefore desirable to which the resources material after renewal is imported.By integrating in the past
The teaching material of making teaches the text data of auxiliary book and speech data corresponding with text data, and text data and speech data are built
Vertical one-to-one relationship, and text database and speech database are formed, and persistence maintenance updates after there is newly revised edition sheet
Database.
Further, Database unit 31 includes：
Identification code indexing unit 311, for text data and speech data corresponding with text data mark is same
Identification code.
Specifically, text data and speech data are established into one-to-one relationship, can be by text data and voice number
One-to-one relationship is realized according to mark identification code, is marked to a text data and with the speech data corresponding to this article notebook data
Same identification code, and the identification code is unique identification code, after to text data and speech data mark identification code, by text
Notebook data and speech data are stored in text database and speech database respectively.
Matching unit 32, for obtaining the text data of speech data to be logged, by the textual data of speech data to be logged
Matched according to the text data in text database.
In embodiments of the present invention, when the resources material after having renewal needs to be imported, resources material is obtained first
Text data, the text data of speech data to be logged is matched with the text data in text database, to obtain
Identical text data, avoid carrying out repeated taping to text data so that speech data is efficiently utilized, will not be because of
There is the resources material after renewal just to give up original speech data.
Further, matching unit 32 includes：Character string acquiring unit 321 and coupling subelement 322, wherein：
Character string acquiring unit 321, the character string of the text data for obtaining speech data to be logged；And
Coupling subelement 322, for the character string of the text data of speech data to be logged to be entered in text database
Row matches character by character.
Specifically, the character string of the text data of speech data to be logged is obtained, by the way that character string is carried out character by character
Match somebody with somebody, obtained in text database with the identical text data of the text data of speech data to be logged, effectively ensure
The accuracy of matching, while improve matching efficiency.
Extraction unit 33, for according to the text data matched, from speech data corresponding to speech database extraction.
In embodiments of the present invention, the text data in the text data and text database of speech data to be logged is entered
Row matching, after obtaining matching identical text data, from speech data corresponding to speech database extraction, avoid identical
The drawbacks of text data repeated taping, the importing time of new resources material is improved, efficiently utilize existing voice number
According to.
Further, extraction unit 33 includes：Identification code acquiring unit 331 and extraction subelement 332, wherein：
Identification code acquiring unit 331, for obtaining the identification code of matched text data；And
Subelement 332 is extracted, the speech data for the same identification code of extraction mark in speech database.
Specifically, after identical text data is matched, the text data matched in text database is read only
One identification code, according to the identification code, the speech data for being marked with the identification code is extracted in speech database.
In embodiments of the present invention, text data and speech data are formed into one-to-one relation, passes through matched text
Data, existing same voice data in extraction speech database are realized, avoid repeated taping so that speech data can obtain
To recycling, reduce recording demand, so as to reduce cost.
Example IV：
Fig. 4 shows the structural representation of the input device for the speech data that the embodiment of the present invention four provides, for the ease of
Illustrate, illustrate only the part related to the embodiment of the present invention.In embodiments of the present invention, the input device bag of speech data
Include：Database unit 41, matching unit 42, extraction unit 43 and recoding unit 44, wherein：
Database unit 41, for text data and speech data corresponding with text data to be formed one a pair
It should be related to, and establish text database and speech database respectively；
Matching unit 42, for obtaining the text data of speech data to be logged, by the textual data of speech data to be logged
Matched according to the text data in text database；
Extraction unit 43, for according to the text data matched, from speech data corresponding to speech database extraction；With
And
Recoding unit 44, if for being not matched to same text data in text database, obtained by recording
Speech data corresponding with text data.
In embodiments of the present invention, when being not matched to same text data in text database, then need to pass through
Speech data corresponding to recording acquisition.Specifically, can be by the way that text data be split, the character after being split, according to
Voice corresponding to secondary acquisition character, and these voices are combined to the speech data to form corresponding text data successively.
In embodiments of the present invention, each unit of the input device of speech data can be real by corresponding hardware or software unit
Existing, each unit can be independent soft and hardware unit, can also be integrated into a soft and hardware unit, herein not limiting
Invention.The embodiment of the device each unit specifically refers to the description of previous embodiment one, will not be repeated here.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (10)
1. a kind of input method of speech data, it is characterised in that methods described comprises the steps：
Text data and speech data corresponding with the text data are formed into one-to-one relationship, and establish text respectively
Database and speech database；
The text data of speech data to be logged is obtained, by the text data of the speech data to be logged and the text data
Text data in storehouse is matched；
According to the text data matched, from speech data corresponding to speech database extraction.
2. the method as described in claim 1, it is characterised in that by text data and voice corresponding with the text data
Data form one-to-one relationship, and the step of establish text database and speech database respectively, including：
Text data and speech data corresponding with the text data are marked into same identification code.
3. the method as described in claim 1, it is characterised in that according to the text data matched, extracted from speech database
The step of corresponding speech data, including：
Obtain the identification code of matched text data；
Extraction marks the speech data of same identification code in the speech database.
4. the method as described in claim 1, it is characterised in that obtain the text data of speech data to be logged, treated described
The step of text data of typing speech data is matched with the text data in the text database, including：
Obtain the character string of the text data of speech data to be logged；
The character string of the text data of the speech data to be logged is matched character by character in text database.
5. the method as described in claim 1, it is characterised in that methods described also includes：
If being not matched to same text data in the text database, obtained and the text data pair by recording
The speech data answered.
6. a kind of input device of speech data, it is characterised in that described device includes：
Database unit, corresponded for text data and speech data corresponding with the text data to be formed
Relation, and text database and speech database are established respectively；
Matching unit, for obtaining the text data of speech data to be logged, by the text data of the speech data to be logged
Matched with the text data in the text database；And
Extraction unit, for according to the text data matched, from speech data corresponding to speech database extraction.
7. device as claimed in claim 6, it is characterised in that the Database unit includes：
Identification code indexing unit, for text data and speech data corresponding with the text data to be marked into same mark
Code.
8. device as claimed in claim 6, it is characterised in that the extraction unit includes：
Identification code acquiring unit, for obtaining the identification code of matched text data；And
Subelement is extracted, the speech data for the same identification code of extraction mark in the speech database.
9. device as claimed in claim 6, it is characterised in that the matching unit includes：
Character string acquiring unit, the character string of the text data for obtaining speech data to be logged；And
Coupling subelement, for the character string of the text data of the speech data to be logged is carried out in text database by
Character match.
10. device as claimed in claim 6, it is characterised in that the system also includes：
Recoding unit, if for being not matched to same text data in the text database, by record obtain with
Speech data corresponding to the text data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611100679.7A CN107480159A (en) | 2016-12-02 | 2016-12-02 | The input method and device of a kind of speech data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611100679.7A CN107480159A (en) | 2016-12-02 | 2016-12-02 | The input method and device of a kind of speech data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107480159A true CN107480159A (en) | 2017-12-15 |
Family
ID=60594737
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611100679.7A Pending CN107480159A (en) | 2016-12-02 | 2016-12-02 | The input method and device of a kind of speech data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107480159A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111667815A (en) * | 2020-06-04 | 2020-09-15 | 上海肇观电子科技有限公司 | Method, apparatus, chip circuit and medium for text-to-speech conversion |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1254786C (en) * | 2004-06-01 | 2006-05-03 | 安徽中科大讯飞信息科技有限公司 | Method for synthetic output with prompting sound and text sound in speech synthetic system |
| CN101908053A (en) * | 2009-11-27 | 2010-12-08 | 新奥特（北京）视频技术有限公司 | Voice retrieval method and device |
| CN102723004A (en) * | 2011-03-29 | 2012-10-10 | 汉王科技股份有限公司 | Electronic document point-reading control method and apparatus |
| CN103366010A (en) * | 2013-07-25 | 2013-10-23 | 北京小米科技有限责任公司 | Method and device for searching audio file |
-
2016
- 2016-12-02 CN CN201611100679.7A patent/CN107480159A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1254786C (en) * | 2004-06-01 | 2006-05-03 | 安徽中科大讯飞信息科技有限公司 | Method for synthetic output with prompting sound and text sound in speech synthetic system |
| CN101908053A (en) * | 2009-11-27 | 2010-12-08 | 新奥特（北京）视频技术有限公司 | Voice retrieval method and device |
| CN102723004A (en) * | 2011-03-29 | 2012-10-10 | 汉王科技股份有限公司 | Electronic document point-reading control method and apparatus |
| CN103366010A (en) * | 2013-07-25 | 2013-10-23 | 北京小米科技有限责任公司 | Method and device for searching audio file |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111667815A (en) * | 2020-06-04 | 2020-09-15 | 上海肇观电子科技有限公司 | Method, apparatus, chip circuit and medium for text-to-speech conversion |
| CN111667815B (en) * | 2020-06-04 | 2023-09-01 | 上海肇观电子科技有限公司 | Method, apparatus, chip circuit and medium for text-to-speech conversion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liebowitz | Big data and business analytics | |
| CN106575166B (en) | Method for processing hand input character, splitting and merging data and processing encoding and decoding | |
| HK1121266A1 (en) | System and method for searching and matching data having ideogrammatic content | |
| CA2610208A1 (en) | Learning facts from semi-structured text | |
| CN106776538A (en) | The information extracting method of enterprise's noncanonical format document | |
| WO2009066501A1 (en) | Information search method, device, and program, and computer-readable recording medium | |
| CN103778131A (en) | Caption query method and device, video player and caption query server | |
| CN107203574A (en) | Data management and the polymerization of data analysis | |
| CN104021219A (en) | Method and device for generating data template | |
| CN102567423A (en) | Method and system for associated search of poetry | |
| CN106601253A (en) | Important-field intelligent robot character broadcast and reading check and proofreading method and system | |
| CN104517068A (en) | Audio file processing method and equipment | |
| CN107480159A (en) | The input method and device of a kind of speech data | |
| CN107679567B (en) | Code copying behavior identification method, device and system | |
| CN104850580B (en) | A kind of method of mark and retrieval teaching resource on the internet | |
| CN103164534A (en) | Method and system of data search based on cloud education platform | |
| CN103164536B (en) | A kind of method and system realizing cloud education platform data search | |
| CN102609410A (en) | Authority file auxiliary writing system and authority file generating method | |
| CN102375864A (en) | Page management method and device | |
| CN101017503A (en) | Multiple layouts e-card machine and manufacture method of multiple layouts e-card | |
| CN107885832A (en) | A kind of figurative mark search method | |
| KR102119724B1 (en) | Terminal device for supporting quick search for video and operating method thereof | |
| EP1522027B8 (en) | Method and system of creating and using chinese language data and user-corrected data | |
| CN109858866A (en) | Personal file file forming method and system | |
| CN107403399A (en) | A kind of Training Methodology based on multimedia teaching |
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 |
Application publication date: 20171215 |
|
| RJ01 | Rejection of invention patent application after publication |