CN109165392A - Interaction language translating method and device - Google Patents
Interaction language translating method and device Download PDFInfo
- Publication number
- CN109165392A CN109165392A CN201811003104.2A CN201811003104A CN109165392A CN 109165392 A CN109165392 A CN 109165392A CN 201811003104 A CN201811003104 A CN 201811003104A CN 109165392 A CN109165392 A CN 109165392A
- Authority
- CN
- China
- Prior art keywords
- translated
- information
- translation
- audio source
- source data
- 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 28
- 230000003993 interaction Effects 0.000 title claims abstract description 15
- 238000013519 translation Methods 0.000 claims abstract description 82
- 239000000284 extract Substances 0.000 claims abstract description 14
- 238000005192 partition Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 238000009434 installation Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 5
- 230000007306 turnover Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
-
- 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
- G10L15/005—Language recognition
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a kind of interaction language translating method and devices, wherein the described method includes: audio source data to be translated is obtained, voice data of the audio source data packet containing various time points in timing；Extract and parse the voice data of audio source data various time points；Search voiced translation information corresponding with voice data；Voiced translation information is combined according to the sequence of various time points in timing to generate corresponding voiced translation text.Scheme disclosed by the invention enables to user that can carry out translation on line to one section of recording or actual conversation, improves the efficiency and flexibility of translation.
Description
Technical field
The invention belongs to language translation technical fields, and in particular to a kind of interaction language translating method and device.
Background technique
With the rapid development of economy, foreign exchanges are more and more extensive, and language obstacle is external for many people
One big obstacle of exchange.To solve the above-mentioned problems, occur various interpreting equipments in the market.Interpreting equipment by feat of
Small and exquisite portable appearance, powerful language translation function, the deep welcome by the vast personage for having language translation demand are also simultaneously
The good assistant of people's foreign language studying.
Nowadays, the fast development of computer, cloud computing and mobile Internet is so that deep learning, intelligent cloud are translated
Through possessing considerable instant translation ability.But translation service provided by existing language translator only provides text mostly
The translation on line of word, although such interpretation method translation accuracy rate is higher, translation efficiency is lower, especially short in needs
In the case where translating in time to certain section of words, flexibility is poor, reduces the use feeling of user.
Therefore, how to carry out translation on line to sound and graphic language becomes technical problem urgently to be resolved.
Summary of the invention
The technical problem to be solved in the present invention is that how to carry out translation on line to voice language.
For this purpose, according in a first aspect, the embodiment of the invention discloses a kind of interaction language translating methods, comprising: obtain to be translated
Audio source data, voice data of the audio source data packet containing various time points in timing；It extracts and to parse audio source data each
The voice data at time point；Search voiced translation information corresponding with voice data；By voiced translation information according to each in timing
The sequence at a time point is combined to generate corresponding voiced translation text.
Optionally, further includes: obtain the partition data of image to be translated, partition data include in image each section wait turn over
The text information translated；It extracts text information to be translated and is searched and text information to be translated according to text information to be translated
Corresponding character translation information；Character translation information is combined by span order to generate corresponding character translation text.
Optionally, the voice messaging for extracting and parsing audio source data various time points includes: to parse audio source data simultaneously
Processing signal is generated, processing signal is for being filtered audio source data.
Optionally, the partition data for obtaining image include: extract image to be translated each adjacent sectors edge it is to be translated
Edge text information；Group merges the edge text information of parsing adjacent sectors to obtain cypher information.
According to second aspect, the embodiment of the invention provides a kind of language translation devices, comprising: audio obtains module, uses
In acquisition audio source data to be translated, voice data of the audio source data packet containing various time points in timing；Voice extraction module,
For extracting and parsing the voice data of audio source data various time points；Searching module is translated, for lookup and voice data
Corresponding voiced translation information；Voiced translation module, for the sequence by voiced translation information according to various time points in timing
It is combined to generate corresponding voiced translation text.
Optionally, further includes: partition data module obtains the partition data of image to be translated, and partition data includes image
The text information to be translated in interior each section；Word Input module, for extracting text information to be translated and according to be translated
Text information search corresponding with text information to be translated character translation information；Character translation module, for turning over text
Information is translated to be combined by span order to generate corresponding character translation text.
Optionally, voice extraction module includes: filter processing unit, for parsing audio source data and generating processing letter
Number, processing signal is for being filtered audio source data.
Optionally, partition data module includes: edge extracting unit, for extracting each adjacent sectors side of image to be translated
Edge edge text information to be translated；Cypher unit merges the edge text information of parsing adjacent sectors for group to obtain
Obtain cypher information.
According to the third aspect, the present invention provides a kind of computer installation, including processor, processor is for executing storage
The computer program stored in device realizes the interaction language translating method of above-mentioned first aspect any one.
According to fourth aspect, the present invention provides a kind of computer readable storage mediums, are stored thereon with computer program,
Processor is for executing the language translation side that the computer program stored in storage medium realizes above-mentioned first aspect any one
Method.
The beneficial effects of the present invention are:
A kind of interaction language translating method and device disclosed by the embodiments of the present invention obtain the audio-source number for needing to translate first
According to accessed audio metadata is extracted and is parsed, to obtain the voice messaging in various time points, according to voice
Information searching voiced translation information corresponding with voice messaging, voiced translation information in turn is combined to generate voice
Cypher text.Scheme disclosed by the embodiments of the present invention allows users to carry out translation on line to one section of recording or actual conversation,
Improve the efficiency and flexibility of translation.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those skilled in the art, without creative efforts,
It is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of interaction language translating method of the embodiment of the present invention；
Fig. 2 is a kind of structural schematic diagram of language translation device of the embodiment of the present invention.
Specific embodiment
Technical solution of the present invention is clearly and completely described below in conjunction with attached drawing, it is clear that described implementation
Example is a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill
Personnel's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Referring to FIG. 1, for a kind of interaction language translating method flow chart disclosed in the present embodiment, which includes:
Step S101 obtains audio source data to be translated.
In a particular embodiment, language translation device can carry out real-time online to language such as one section of recording, one section of dialogues
Translation, in the present embodiment, voice messaging of the audio source data packet containing various time points in timing.
Step S102 extracts and parses the voice data of audio source data various time points.
In a particular embodiment, the voice messaging for extracting and parsing audio source data various time points includes: parsing audio
Source data simultaneously generates processing signal, and processing signal is for being filtered audio source data.
It is filtered the interference that on the one hand can reduce audio-source internal noise to audio source data, on the other hand can
The voice messaging at time point each in timing in audio-source is reinforced by being filtered, in order to be mentioned to voice messaging
It takes and parses, while also supporting the translation of dialect to a certain extent.
Step S103 searches voiced translation information corresponding with voice data.
Voice corresponding with the voice messaging extracted is searched in language database according to the voice messaging extracted to turn over
Translate information.
Voiced translation information is combined according to the sequence of various time points in timing corresponding to generate by step S104
Voiced translation text.
The voiced translation information found is combined arrangement according to various time points in timing, make its put in order with
The voice messaging of various time points corresponds in timing, ultimately generates corresponding voiced translation text.
In an alternate embodiment of the invention, after executing step S104, further includes: the partition data of image to be translated is obtained,
Partition data includes the text information to be translated in each section in image；Extract text information to be translated and according to be translated
Text information searches character translation information corresponding with text information to be translated；Character translation information is carried out by span order
Combination is to generate corresponding character translation text.
By carrying out subregion to image, it can be improved the accuracy of image interpretation, extract in the image after subregion wait turn over
The text information translated, and character translation information corresponding with text information is searched according to the text information extracted, it finally will be literary
Word translation information is combined arrangement according to section, so that it is put in order and puts in order one with the text information to be translated extracted
It causes, ultimately generates corresponding image interpretation text.
In the specific implementation process, the partition data for obtaining image includes: each adjacent sectors side for extracting image to be translated
Edge edge text information to be translated；Group merges the edge text information of parsing adjacent sectors to obtain cypher information.
The edge text information at subregion edge is individually extracted and combined, according to the side before combination and/or after combination
Edge text information, which carries out searching in database, obtains cypher information, turns over when allowing to improve word or text interlacing separately
The accuracy translated.
The present embodiment also discloses a kind of language translation device, referring to FIG. 2, illustrating for the language translation apparatus structure
Figure, the language translation device include:
Audio obtains module 201, and for obtaining audio source data to be translated, audio source data packet is containing each time in timing
The voice data of point；Voice extraction module 202, for extracting and parsing the voice data of audio source data various time points；It turns over
Searching module 203 is translated, for searching voiced translation information corresponding with voice data；Voiced translation module 204 is used for voice
Translation information is combined to generate corresponding voiced translation text according to the sequence of various time points in timing.
In the specific implementation process, voice extraction module 202 includes: filter processing unit, for parsing audio source data
And processing signal is generated, processing signal is for being filtered audio source data.
In optionally embodiment, which can also include: partition data module, obtain image to be translated
Partition data, partition data include image in each section text information to be translated；Word Input module, for extract to
The text information of translation simultaneously searches character translation information corresponding with text information to be translated according to text information to be translated；
Character translation module, for being combined character translation information by span order to generate corresponding character translation text.
In the specific implementation process, partition data module includes: edge extracting unit, for extracting each of image to be translated
Adjacent sectors edge edge text information to be translated；Cypher unit, for a group edge text for merging parsing adjacent sectors
Word information is to obtain cypher information.
In addition, also providing a kind of computer installation in the embodiment of the present invention, processor, which passes through, executes the computer instruction,
To realize following methods:
Obtain audio source data to be translated, voice data of the audio source data packet containing various time points in timing；It extracts simultaneously
Parse the voice data of audio source data various time points；Search voiced translation information corresponding with voice data；Voice is turned over
Information is translated to be combined according to the sequence of various time points in timing to generate corresponding voiced translation text.
It is that can lead to it will be understood by those skilled in the art that realizing all or part of the process in above-described embodiment method
Computer program is crossed to instruct relevant hardware and complete, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (ROM) or random access memory (RAM) etc..Computer processor is situated between for executing storage
The computer program stored in matter realizes following methods:
Obtain audio source data to be translated, voice data of the audio source data packet containing various time points in timing；It extracts simultaneously
Parse the voice data of audio source data various time points；Search voiced translation information corresponding with voice data；Voice is turned over
Information is translated to be combined according to the sequence of various time points in timing to generate corresponding voiced translation text.
What has been described above is only an embodiment of the present invention, and the common sense such as well known specific structure and characteristic are not made herein in scheme
Excessive description.It, without departing from the structure of the invention, can be with it should be pointed out that for those skilled in the art
Make several modifications and improvements.These also should be considered as protection scope of the present invention, these all will not influence what the present invention was implemented
Effect and patent practicability.The scope of protection required by this application should be based on the content of the claims, in specification
The records such as specific embodiment can be used for explaining the content of claim.
Claims (10)
1. a kind of interaction language translating method characterized by comprising
Obtain audio source data to be translated, the voice data of the audio source data packet containing various time points in timing；
Extract and parse the voice data of the audio source data various time points；
Search voiced translation information corresponding with the voice data；
The voiced translation information is combined according to the sequence of various time points in timing to generate corresponding voiced translation
Text.
2. interaction language translating method as described in claim 1, which is characterized in that further include:
The partition data of image to be translated is obtained, the partition data includes the text information to be translated in each section in image；
It extracts the text information to be translated and is searched and the text to be translated according to the text information to be translated
The corresponding character translation information of information；
The character translation information is combined by span order to generate corresponding character translation text.
3. interaction language translating method as described in claim 1, which is characterized in that the extraction and to parse the audio source data each
The voice messaging at a time point includes:
It parses the audio source data and generates processing signal, the processing signal is for being filtered the audio source data
Processing.
4. interaction language translating method as claimed in claim 2, which is characterized in that it is described obtain image partition data include:
Extract each adjacent sectors edge of image to be translated edge text information to be translated；
Group merges the edge text information of parsing adjacent sectors to obtain cypher information.
5. a kind of language translation device characterized by comprising
Audio obtains module, and for obtaining audio source data to be translated, the audio source data packet is containing various time points in timing
Voice data；
Voice extraction module, for extracting and parsing the voice data of the audio source data various time points；
Searching module is translated, for searching voiced translation information corresponding with the voice data；
Voiced translation module, for being combined the voiced translation information according to the sequence of various time points in timing with life
At corresponding voiced translation text.
6. language translation device as claimed in claim 5, which is characterized in that further include:
Partition data module, for obtaining the partition data of image to be translated, the partition data includes each section in image
Text information to be translated；
Word Input module, for extract the text information to be translated and according to the text information to be translated search with
The corresponding character translation information of the text information to be translated；
Character translation module, for being combined the character translation information by span order to generate corresponding character translation
Text.
7. language translation device as claimed in claim 5, which is characterized in that the voice extraction module includes:
Filter processing unit, for parsing the audio source data and generating processing signal, the processing signal is used for described
Audio source data is filtered.
8. language translation device as claimed in claim 6, which is characterized in that the partition data module includes:
Edge extracting unit, each adjacent sectors edge for extracting image to be translated edge text information to be translated；
Cypher unit merges the edge text information of parsing adjacent sectors for group to obtain cypher information.
9. a kind of computer installation, which is characterized in that including processor, the processor is based on executing and storing in memory
Calculation machine program realizes the interaction language translating method such as claim 1-4 any one.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that processor is for executing
The computer program stored in storage medium realizes the interaction language translating method as described in claim 1-4 any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811003104.2A CN109165392A (en) | 2018-08-30 | 2018-08-30 | Interaction language translating method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811003104.2A CN109165392A (en) | 2018-08-30 | 2018-08-30 | Interaction language translating method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109165392A true CN109165392A (en) | 2019-01-08 |
Family
ID=64893402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811003104.2A Pending CN109165392A (en) | 2018-08-30 | 2018-08-30 | Interaction language translating method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109165392A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109992753A (en) * | 2019-03-22 | 2019-07-09 | 维沃移动通信有限公司 | A kind of translation processing method and terminal device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100299147A1 (en) * | 2009-05-20 | 2010-11-25 | Bbn Technologies Corp. | Speech-to-speech translation |
| CN104754536A (en) * | 2013-12-27 | 2015-07-01 | ***通信集团公司 | Method and system for realizing communication between different languages |
| CN107515862A (en) * | 2017-09-01 | 2017-12-26 | 北京百度网讯科技有限公司 | Voice translation method, device and server |
| CN107656922A (en) * | 2017-09-25 | 2018-02-02 | 广东小天才科技有限公司 | Translation method, translation device, translation terminal and storage medium |
-
2018
- 2018-08-30 CN CN201811003104.2A patent/CN109165392A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100299147A1 (en) * | 2009-05-20 | 2010-11-25 | Bbn Technologies Corp. | Speech-to-speech translation |
| CN104754536A (en) * | 2013-12-27 | 2015-07-01 | ***通信集团公司 | Method and system for realizing communication between different languages |
| CN107515862A (en) * | 2017-09-01 | 2017-12-26 | 北京百度网讯科技有限公司 | Voice translation method, device and server |
| CN107656922A (en) * | 2017-09-25 | 2018-02-02 | 广东小天才科技有限公司 | Translation method, translation device, translation terminal and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109992753A (en) * | 2019-03-22 | 2019-07-09 | 维沃移动通信有限公司 | A kind of translation processing method and terminal device |
| CN109992753B (en) * | 2019-03-22 | 2023-09-08 | 维沃移动通信有限公司 | Translation processing method and terminal equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107423363B (en) | Artificial intelligence based word generation method, device, equipment and storage medium | |
| CN104731959B (en) | The method of text based web page contents generation video frequency abstract, apparatus and system | |
| KR101762866B1 (en) | Statistical translation apparatus by separating syntactic translation model from lexical translation model and statistical translation method | |
| US20170287474A1 (en) | Improving Automatic Speech Recognition of Multilingual Named Entities | |
| CN114116994A (en) | Welcome robot dialogue method | |
| CN111046656B (en) | Text processing method, text processing device, electronic equipment and readable storage medium | |
| CN109616096A (en) | Construction method, device, server and the medium of multilingual tone decoding figure | |
| CN104252861A (en) | Video voice conversion method, video voice conversion device and server | |
| CN102662935A (en) | Interactive machine translation method and machine translation system | |
| CN103314369B (en) | Machine translation apparatus and method | |
| CN109256133A (en) | A kind of voice interactive method, device, equipment and storage medium | |
| CN107943786B (en) | Chinese named entity recognition method and system | |
| CN111178076B (en) | Named entity recognition and linking method, device, equipment and readable storage medium | |
| CN103678273A (en) | Internet paragraph level topic recognition system | |
| CN103186522A (en) | Electronic device and natural language analyzing method thereof | |
| CN109710949A (en) | A kind of interpretation method and translator | |
| CN109524008A (en) | Voice recognition method, device and equipment | |
| Zhang et al. | Advances in multi-turn dialogue comprehension: A survey | |
| Wang et al. | Mongolian named entity recognition with bidirectional recurrent neural networks | |
| Palogiannidi et al. | Valence, arousal and dominance estimation for English, German, Greek, Portuguese and Spanish lexica using semantic models. | |
| Schlippe et al. | Unsupervised language model adaptation for automatic speech recognition of broadcast news using web 2.0. | |
| KR20150042533A (en) | Apparatus for analyzing complex sentence, and recording medium therefor | |
| CN109165392A (en) | Interaction language translating method and device | |
| CN106156007A (en) | A kind of English-Chinese statistical machine translation method of word original shape | |
| Deshpande et al. | Natural language query processing using probabilistic context free grammar |
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: 20190108 |
|
| RJ01 | Rejection of invention patent application after publication |