CN105786801A - Speech translation method, communication method and related device - Google Patents
Speech translation method, communication method and related device Download PDFInfo
- Publication number
- CN105786801A CN105786801A CN201410810783.XA CN201410810783A CN105786801A CN 105786801 A CN105786801 A CN 105786801A CN 201410810783 A CN201410810783 A CN 201410810783A CN 105786801 A CN105786801 A CN 105786801A
- Authority
- CN
- China
- Prior art keywords
- voice
- translation
- translated
- speech data
- speech
- 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.)
- Withdrawn
Links
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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Telephonic Communication Services (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a speech translation method, a communication method and a related device, and relates to the field of terminal application. The method comprises the steps of acquiring a first speech; extracting the speech feature of the first speech; converting the first speech, and thereby obtaining translated speech data; and performing speech fitting on the translated speech data according to the speech feature, thus obtaining a second speech. By using the method provided by the invention, the translated second speech can reserve the speech feature of the speaker, so that a more real experience effect can be provided for the listener when the method is applied to the communication of terminals.
Description
Technical field
The present invention relates to terminal applies field, particularly a kind of voice translation method, the means of communication and relevant apparatus.
Background technology
Development along with the development of hardware technology and software, fast development including cloud computing technology, the algorithm that artificial intelligence pattern identifies is made to obtain very big applied environment, various data for including quickly can calculate through a large amount of of cloud computing platform, it is readily obtained good training result so that various phonetic feature storehouses more conform to practical service environment.
The use of the siri application of Apple, excites the use upsurge of various voice technologies in society, and the both hands using intelligent terminal person have been liberated in the development of voice technology further, and the development to social productive forces is also a kind of very big promotion.
Current mobile phone does not possess instant translation function, when the languages of communicating pair are different or there is dialect, there is communication disorders.Therefore, currently need badly a kind of based on the voice technology on cloud computing platform, it is achieved instant translation during communication.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of voice translation method, the means of communication and relevant apparatus, it is possible to the second voice after translation can remain with the phonetic feature of speaker, improve the experience of those who answer.
For solving above-mentioned technical problem, embodiments of the invention provide a kind of voice translation method, including:
Obtain the first voice；
Extract the phonetic feature of described first voice；
Described first voice is changed, the speech data after being translated；
According to described phonetic feature, the speech data after described translation is carried out voice matching, obtain the second voice.
Wherein, described first voice is changed, the speech data after being translated, including:
Based on language database, described first voice is changed, the speech data after being translated.
Wherein, described phonetic feature includes: the fundamental tone of described first voice, or the fundamental tone of described first voice and overtone.
Additionally, embodiments of the invention also provide for a kind of means of communication, it is applied to terminal, including:
After terminal starts communication applications, based on this communication applications, obtain the first voice to be translated；
Extract the phonetic feature of described first voice；
Described first voice is changed, the speech data after being translated；
According to described phonetic feature, the speech data after described translation is carried out voice matching, obtain the second voice；
Export described second voice.
Wherein, based on this communication applications, obtain the first voice of language to be converted, including:
Based on this communication applications, obtain the first voice of the language to be converted that peer user sends over；
Export described second voice, including:
Described second voice is exported to this end subscriber.
Wherein, based on this communication applications, obtain the first voice of language to be converted, also include:
Based on this communication applications, obtain the first voice of the language to be converted of this end subscriber input；
Export described second voice, also include:
Based on this communication applications, export described second voice to peer user.
Additionally, embodiments of the invention also provide for a kind of speech translation apparatus, including:
First acquisition module, is used for obtaining the first voice；
Extraction module, for extracting the phonetic feature of described first voice；
First modular converter, for described first voice is changed, the speech data after being translated；
First fitting module, for the speech data after described translation being carried out voice matching according to described phonetic feature, obtains the second voice.
Wherein, described phonetic feature includes: the fundamental tone of described first voice, or the fundamental tone of described first voice and overtone.
Additionally, embodiments of the invention also provide for a kind of terminal, including:
Second acquisition module, for, after terminal starts communication applications, based on this communication applications, obtaining the first voice of language to be converted；
Second extraction module, for extracting the phonetic feature of described first voice；
Second modular converter, for described first voice is changed, the speech data after being translated；
Second fitting module, for the speech data after described translation being carried out voice matching according to described phonetic feature, obtains the second voice；
Output module, is used for exporting described second voice.
Wherein, described second acquisition module includes:
First obtains submodule, for based on this communication applications, obtaining the first voice of the language to be converted that peer user sends over；
Described output module includes:
First output sub-module, for exporting described second voice to this end subscriber.
Wherein, described second acquisition module also includes:
Second obtains submodule, for based on this communication applications, obtaining first voice to be translated of this end subscriber input；
Described output module also includes:
Second output sub-module, for based on this communication applications, exporting described second voice to peer user.
Having the beneficial effect that of the technique scheme of the present invention:
The solution of the present invention can be translated by ground voice that communication applications is transmitted, thus facilitating the communication between user.Owing to the second voice after translated can retain the phonetic feature of speaker, therefore when VAS application-to-terminal service communication, bring more real experience effect for listening to a side.
Accompanying drawing explanation
Fig. 1 is the step schematic diagram of the voice translation method of the present invention；
Fig. 2 is the step schematic diagram of the means of communication of the present invention；
Fig. 3 is the schematic flow sheet that the means of communication of the present invention are applied to voice call；
Fig. 4 is the schematic flow sheet that the means of communication of the present invention are applied to bitcom；
Fig. 5 is the structural representation of the speech translation apparatus of the present invention；
Fig. 6 is the structural representation of the terminal of the present invention.
Detailed description of the invention
For making the technical problem to be solved in the present invention, technical scheme and advantage clearly, it is described in detail below in conjunction with the accompanying drawings and the specific embodiments.
It is an object of the invention to provide can when communication to one, it is achieved the scheme of instant translation.And existing voiced translation technology, the phonetic feature of speaker can not be retained, therefore there is indisposed sense in the speech data after translation on tone, is unfavorable for that user goes to understand.For solving this problem, the present invention proposes a kind of voice translation method, as it is shown in figure 1, include:
Step 11, obtains the first voice；
Step 12, extracts the phonetic feature of described first voice；
Step 13, changes described first voice, the speech data after being translated；
Step 14, carries out voice matching according to described phonetic feature to the speech data after described translation, obtains the second voice.
Can see that the present embodiment is before translating according to above-mentioned steps 11 to step 14, extract the phonetic feature of primitive sound, and upon translation, according to the phonetic feature extracted, translated speech data is reduced into the tone of speaker, make those who answer obtain more actual experience effect, be beneficial to understanding.
Specifically, in above-mentioned steps 13, based on language database, described first voice is changed, the speech data after being translated.
Exemplarily, language database can be saved in this locality, after getting the first voice, according to local language database the first voice is carried out language identification and translates.Additionally, language database can also be arranged on service end, it is achieved translation on line.Needing to be described, the translation of the present embodiment can be the conversion between languages, or the conversion between same languages difference dialect.
Specifically, described in the present embodiment, phonetic feature includes: the fundamental tone of described first voice, or the fundamental tone of described first voice and overtone.
Fundamental tone is the sound that sounding body body vibration produces, and fundamental tone determines pitch.The sound that sounding body partial vibration produces is called overtone, and overtone determines tone color.The speech data translated can be restored back to the tone that speaker is original by fundamental tone feature by the present embodiment.Preferably, it is also possible in conjunction with overtone feature, the speech data after translation is reduced, it is achieved better effect.
Additionally, another embodiment of the present invention provides a kind of means of communication being applied to terminal, it is possible in real time by the voiced translation of communication one side to communication the opposing party, as in figure 2 it is shown, the described means of communication include:
Step 21, after terminal starts communication applications, based on this communication applications, obtains the first voice to be translated；
Step 22, extracts the phonetic feature of described first voice；
Step 23, changes described first voice, the speech data after being translated；
Step 24, carries out voice matching according to described phonetic feature to the speech data after described translation, obtains the second voice；
Step 25, exports described second voice.
Specifically, translation process can carry out in the terminal receiving side, namely in above-mentioned steps 21, based on the communication applications that terminal is run, obtains the first voice to be translated that peer user sends over；In above-mentioned steps 25, export described second voice to this end subscriber.
In actual applications, the voice sent from opposite end received can be translated by user in the terminal of oneself.
Additionally, translation process can carry out in the terminal of sending side, namely in above-mentioned steps 21, based on the communication applications that terminal is run, obtain first voice to be translated of this end subscriber input；In above-mentioned steps 25, based on the communication applications that terminal is run, export described second voice to peer user.
In actual applications, user can translate saying voice in the terminal of oneself, is then forwarded to opposite end afterwards.Even if opposite equip. is provided without the scheme of the present embodiment, the voice after translation also can be received, thus realizing normal communication.
Below the application scenarios of the means of communication of the present invention is introduced.
<application scenarios one>
In application scenarios one, communication two party is voice call, and calling terminal retransmits to called end, as in figure 2 it is shown, detailed process includes after being converted to Shanghai language for Guangdong language calling subscribe said:
A1, calling terminal configures translation system, and the language feature storehouse of configuration translation system, such as the composite character storehouse of configuration Fujian Guangdong language with Shanghai language；
A2, calling terminal and terminal called set up voice call, are obtained the first voice of calling subscribe's input by calling terminal mike；
A3, calling terminal extracts the fundamental tone (can also include overtone) of the first voice；
A4, the first voice, based on composite character storehouse, is changed by calling terminal, the speech data after being translated；
A5, the speech data after translation is carried out voice matching according to the fundamental tone extracted by calling terminal, obtains meeting calling subscribe and speaks the second voice of tone.
A6, the second voice is carried out speech processes and modulates by calling terminal；
A7, modulation signal is sent to terminal called by calling terminal, and terminal called receives after being adjusted to signal and carries out demodulation process, obtains and plays the second voice.The second voice now play at terminal called has been the Shanghai language after translation.
In application scenarios one, terminal called is made without additional configuration, and therefore this programme has higher practicality.Additionally, calling terminal only can send the second voice after translating to terminal called, it is to avoid called subscriber is brought interference by the first voice.
<application scenarios two>
In application scenarios two, communication two party is conversed based on MSN, and terminal called, after receiving the japanese voice file that calling subscribe sends, is translated into Chinese, and plays to called subscriber, and detailed process includes:
B1, arranges Japanese Translator software on terminal called, and allows MSN to call Japanese Translator software；
B2, called subscriber obtains and preserves the japanese voice file sent from calling subscribe by MSN；
B3, MSN extracts the fundamental tone of described japanese voice file, and calls Japanese Translator software this japanese voice file is translated, and obtains Chinese speech file；
B4, Chinese speech file, by the fundamental tone extracted, is carried out voice matching, makes Chinese speech file be reduced to the tone of calling subscribe by MSN；
B5, MSN can but japanese voice file before not necessarily the Chinese speech file after matching being replaced translation preserve, and operated by called subscriber or automatically the Chinese speech literary composition preserved played to called subscriber.
In application scenarios two, the voiced translation software that translation steps can be provided by third party performs, and MSN has only to call voiced translation software and can carry out real-time voiced translation.In actual applications, called subscriber can download according to the translation demand of oneself and install the translation APP of correspondence, afterwards with translation APP, MSN is associated binding.
Additionally, another embodiment of the present invention also provides for a kind of speech translation apparatus, as it is shown in figure 5, include:
First acquisition module, is used for obtaining the first voice；
Extraction module, for extracting the phonetic feature of described first voice；
First modular converter, for described first voice is changed, the speech data after being translated；
First fitting module, for the speech data after described translation being carried out voice matching according to described phonetic feature, obtains the second voice.
Wherein, described phonetic feature includes: the fundamental tone of described first voice, or the fundamental tone of described first voice and overtone.
The speech translation apparatus of the present embodiment, before translating, extracts the phonetic feature of primitive sound, and upon translation, translated speech data is reduced into according to the phonetic feature extracted the tone of speaker, make the more convenient understanding of those who answer.
Obviously, the speech translation apparatus of the present embodiment is corresponding with voice translation method mentioned above, is all capable of same technique effect.
Additionally, embodiments of the invention also provide for a kind of terminal, as shown in Figure 6, including:
Second acquisition module, for, after terminal starts communication applications, based on this communication applications, obtaining the first voice of language to be converted；
Second extraction module, for extracting the phonetic feature of described first voice；
Second modular converter, for described first voice is changed, the speech data after being translated；
Second fitting module, for the speech data after described translation being carried out voice matching according to described phonetic feature, obtains the second voice；
Output module, is used for exporting described second voice.
Wherein, described second acquisition module includes:
First obtains submodule, for based on this communication applications, obtaining the first voice of the language to be converted that peer user sends over；
Described output module includes:
First output sub-module, for exporting described second voice to this end subscriber.
Additionally, on above-mentioned basis, described second acquisition module also includes:
Second obtains submodule, for based on this communication applications, obtaining first voice to be translated of this end subscriber input；
Described output module also includes:
Second output sub-module, for based on this communication applications, exporting described second voice to peer user.
Obviously, the terminal of the present embodiment is corresponding with the means of communication mentioned above, all can reach identical technique effect.
The above is the preferred embodiment of the present invention; it should be pointed out that, for those skilled in the art, under the premise without departing from principle of the present invention; can also making some improvements and modifications, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (11)
1. a voice translation method, it is characterised in that including:
Obtain the first voice；
Extract the phonetic feature of described first voice；
Described first voice is changed, the speech data after being translated；
According to described phonetic feature, the speech data after described translation is carried out voice matching, obtain the second voice.
2. voice translation method according to claim 1, it is characterised in that
Described first voice is changed, the speech data after being translated, including:
Based on language database, described first voice is changed, the speech data after being translated.
3. voice translation method according to claim 1, it is characterised in that
Described phonetic feature includes: the fundamental tone of described first voice, or the fundamental tone of described first voice and overtone.
4. means of communication, are applied to terminal, it is characterised in that including:
After terminal starts communication applications, based on this communication applications, obtain the first voice to be translated；
Extract the phonetic feature of described first voice；
Described first voice is changed, the speech data after being translated；
According to described phonetic feature, the speech data after described translation is carried out voice matching, obtain the second voice；Export described second voice.
5. the means of communication according to claim 4, it is characterised in that
Based on this communication applications, obtain the first voice of language to be converted, including:
Based on this communication applications, obtain the first voice of the language to be converted that peer user sends over；
Export described second voice, including:
Described second voice is exported to this end subscriber.
6. the means of communication according to claim 4, it is characterised in that
Based on this communication applications, obtain the first voice of language to be converted, also include:
Based on this communication applications, obtain the first voice of the language to be converted of this end subscriber input；
Export described second voice, also include:
Based on this communication applications, export described second voice to peer user.
7. a speech translation apparatus, it is characterised in that including:
First acquisition module, is used for obtaining the first voice；
Extraction module, for extracting the phonetic feature of described first voice；
First modular converter, for described first voice is changed, the speech data after being translated；
First fitting module, for the speech data after described translation being carried out voice matching according to described phonetic feature, obtains the second voice.
8. speech translation apparatus according to claim 7, it is characterised in that
Described phonetic feature includes: the fundamental tone of described first voice, or the fundamental tone of described first voice and overtone.
9. a terminal, it is characterised in that including:
Second acquisition module, for, after terminal starts communication applications, based on this communication applications, obtaining the first voice of language to be converted；
Second extraction module, for extracting the phonetic feature of described first voice；
Second modular converter, for described first voice is changed, the speech data after being translated；
Second fitting module, for the speech data after described translation being carried out voice matching according to described phonetic feature, obtains the second voice；
Output module, is used for exporting described second voice.
10. terminal according to claim 9, it is characterised in that
Described second acquisition module includes:
First obtains submodule, for based on this communication applications, obtaining the first voice of the language to be converted that peer user sends over；
Described output module includes:
First output sub-module, for exporting described second voice to this end subscriber.
11. terminal according to claim 9, it is characterised in that
Described second acquisition module also includes:
Second obtains submodule, for based on this communication applications, obtaining first voice to be translated of this end subscriber input；
Described output module also includes:
Second output sub-module, for based on this communication applications, exporting described second voice to peer user.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410810783.XA CN105786801A (en) | 2014-12-22 | 2014-12-22 | Speech translation method, communication method and related device |
| PCT/CN2015/082390 WO2016101571A1 (en) | 2014-12-22 | 2015-06-25 | Voice translation method, communication method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410810783.XA CN105786801A (en) | 2014-12-22 | 2014-12-22 | Speech translation method, communication method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105786801A true CN105786801A (en) | 2016-07-20 |
Family
ID=56149130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410810783.XA Withdrawn CN105786801A (en) | 2014-12-22 | 2014-12-22 | Speech translation method, communication method and related device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105786801A (en) |
| WO (1) | WO2016101571A1 (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106919562A (en) * | 2017-04-28 | 2017-07-04 | 深圳市大乘科技股份有限公司 | A kind of real-time translation system, method and device |
| CN107170453A (en) * | 2017-05-18 | 2017-09-15 | 百度在线网络技术（北京）有限公司 | Across languages phonetic transcription methods, equipment and computer-readable recording medium based on artificial intelligence |
| CN107248947A (en) * | 2017-05-22 | 2017-10-13 | 腾讯科技（深圳）有限公司 | Expression processing method and processing device, computer equipment and storage medium |
| CN107945806A (en) * | 2017-11-10 | 2018-04-20 | 北京小米移动软件有限公司 | User identification method and device based on sound characteristic |
| CN108231062A (en) * | 2018-01-12 | 2018-06-29 | 科大讯飞股份有限公司 | A kind of voice translation method and device |
| WO2019000619A1 (en) * | 2017-06-27 | 2019-01-03 | 深圳市沃特沃德股份有限公司 | Translation method, translation device and translation system |
| WO2019071541A1 (en) * | 2017-10-12 | 2019-04-18 | 深圳市沃特沃德股份有限公司 | Voice translation method, apparatus, and terminal device |
| CN110164414A (en) * | 2018-11-30 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Method of speech processing, device and smart machine |
| WO2019165748A1 (en) * | 2018-02-28 | 2019-09-06 | 科大讯飞股份有限公司 | Speech translation method and apparatus |
| CN110516238A (en) * | 2019-08-20 | 2019-11-29 | 广州国音智能科技有限公司 | Voice translation method, device, terminal and computer storage medium |
| CN112201224A (en) * | 2020-10-09 | 2021-01-08 | 北京分音塔科技有限公司 | Method, equipment and system for simultaneous translation of instant call |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050234702A1 (en) * | 2004-04-14 | 2005-10-20 | Shiho Komiya | Translation support system, server, translation support method, recording medium and computer data signal |
| CN101155291A (en) * | 2006-09-27 | 2008-04-02 | 株式会社东芝 | Apparatus, method and computer program product for translating speech, and terminal that outputs translated speech |
| US20080133245A1 (en) * | 2006-12-04 | 2008-06-05 | Sehda, Inc. | Methods for speech-to-speech translation |
| CN101373592A (en) * | 2007-08-21 | 2009-02-25 | 株式会社东芝 | Speech translation apparatus and method |
| CN101727904A (en) * | 2008-10-31 | 2010-06-09 | 国际商业机器公司 | Voice translation method and device |
| CN102196100A (en) * | 2010-03-04 | 2011-09-21 | 深圳富泰宏精密工业有限公司 | Instant call translation system and method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103258539B (en) * | 2012-02-15 | 2015-09-23 | 展讯通信（上海）有限公司 | A kind of transform method of voice signal characteristic and device |
| CN103810158A (en) * | 2012-11-07 | 2014-05-21 | 中国移动通信集团公司 | Speech-to-speech translation method and device |
-
2014
- 2014-12-22 CN CN201410810783.XA patent/CN105786801A/en not_active Withdrawn
-
2015
- 2015-06-25 WO PCT/CN2015/082390 patent/WO2016101571A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050234702A1 (en) * | 2004-04-14 | 2005-10-20 | Shiho Komiya | Translation support system, server, translation support method, recording medium and computer data signal |
| CN101155291A (en) * | 2006-09-27 | 2008-04-02 | 株式会社东芝 | Apparatus, method and computer program product for translating speech, and terminal that outputs translated speech |
| US20080133245A1 (en) * | 2006-12-04 | 2008-06-05 | Sehda, Inc. | Methods for speech-to-speech translation |
| CN101373592A (en) * | 2007-08-21 | 2009-02-25 | 株式会社东芝 | Speech translation apparatus and method |
| CN101727904A (en) * | 2008-10-31 | 2010-06-09 | 国际商业机器公司 | Voice translation method and device |
| CN102196100A (en) * | 2010-03-04 | 2011-09-21 | 深圳富泰宏精密工业有限公司 | Instant call translation system and method |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106919562A (en) * | 2017-04-28 | 2017-07-04 | 深圳市大乘科技股份有限公司 | A kind of real-time translation system, method and device |
| CN106919562B (en) * | 2017-04-28 | 2024-01-05 | 深圳市大乘科技股份有限公司 | Real-time translation system, method and device |
| CN107170453A (en) * | 2017-05-18 | 2017-09-15 | 百度在线网络技术（北京）有限公司 | Across languages phonetic transcription methods, equipment and computer-readable recording medium based on artificial intelligence |
| US10796700B2 (en) | 2017-05-18 | 2020-10-06 | Baidu Online Network Technology (Beijing) Co., Ltd. | Artificial intelligence-based cross-language speech transcription method and apparatus, device and readable medium using Fbank40 acoustic feature format |
| CN107248947A (en) * | 2017-05-22 | 2017-10-13 | 腾讯科技（深圳）有限公司 | Expression processing method and processing device, computer equipment and storage medium |
| CN107248947B (en) * | 2017-05-22 | 2019-01-08 | 腾讯科技（深圳）有限公司 | Expression processing method and processing device, computer equipment and storage medium |
| WO2019000619A1 (en) * | 2017-06-27 | 2019-01-03 | 深圳市沃特沃德股份有限公司 | Translation method, translation device and translation system |
| WO2019071541A1 (en) * | 2017-10-12 | 2019-04-18 | 深圳市沃特沃德股份有限公司 | Voice translation method, apparatus, and terminal device |
| CN107945806B (en) * | 2017-11-10 | 2022-03-08 | 北京小米移动软件有限公司 | User identification method and device based on sound characteristics |
| CN107945806A (en) * | 2017-11-10 | 2018-04-20 | 北京小米移动软件有限公司 | User identification method and device based on sound characteristic |
| CN108231062A (en) * | 2018-01-12 | 2018-06-29 | 科大讯飞股份有限公司 | A kind of voice translation method and device |
| WO2019165748A1 (en) * | 2018-02-28 | 2019-09-06 | 科大讯飞股份有限公司 | Speech translation method and apparatus |
| CN110164414A (en) * | 2018-11-30 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Method of speech processing, device and smart machine |
| CN110164414B (en) * | 2018-11-30 | 2023-02-14 | 腾讯科技（深圳）有限公司 | Voice processing method and device and intelligent equipment |
| CN110516238B (en) * | 2019-08-20 | 2023-12-19 | 广州国音智能科技有限公司 | Speech translation method, device, terminal and computer storage medium |
| CN110516238A (en) * | 2019-08-20 | 2019-11-29 | 广州国音智能科技有限公司 | Voice translation method, device, terminal and computer storage medium |
| CN112201224A (en) * | 2020-10-09 | 2021-01-08 | 北京分音塔科技有限公司 | Method, equipment and system for simultaneous translation of instant call |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2016101571A1 (en) | 2016-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105786801A (en) | Speech translation method, communication method and related device | |
| CN106919562B (en) | Real-time translation system, method and device | |
| CN108777751A (en) | A kind of call center system and its voice interactive method, device and equipment | |
| CN106156009A (en) | Voice translation method and device | |
| CN1920945B (en) | Tone contour transformation of speech | |
| CN102932539B (en) | Terminal and method based on voice identification | |
| CN105049646B (en) | Change of voice call method, device and terminal | |
| CN104125548B (en) | A kind of method, apparatus and system translated to call language | |
| CN107993646A (en) | A kind of method for realizing real-time voice intertranslation | |
| CN103533129B (en) | Real-time voiced translation communication means, system and the communication apparatus being applicable | |
| CN109360565A (en) | A method of precision of identifying speech is improved by establishing resources bank | |
| CN102257566A (en) | Method and system for adapting communications | |
| CN105206273B (en) | Voice transfer control method and system | |
| CN103730117A (en) | Self-adaptation intelligent voice device and method | |
| CN109756635A (en) | Phone customer service analogy method, device, storage medium and electronic equipment based on WEB | |
| CN103474075A (en) | Method and system for sending voice signals, and method and system for receiving voice signals | |
| US20230247131A1 (en) | Presentation of communications | |
| CN106911832A (en) | A kind of method and device of voice record | |
| CN206249309U (en) | A kind of talkback unit for realizing real-time voice intertranslation | |
| CN206649899U (en) | A kind of communicator for realizing real-time voice intertranslation | |
| CN206312136U (en) | A kind of portable synchronous translation device | |
| CN105915357A (en) | Text information push method for conference content of fragmented asynchronous conference system | |
| US11431767B2 (en) | Changing a communication session | |
| CN106657539A (en) | Vehicle-mounted multifunctional operation-free intelligent service device | |
| CN105933130A (en) | Fragmented asynchronous conference system voice information push method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20160720 |