CN103956167A - Visual sign language interpretation method and device based on Web - Google Patents
Visual sign language interpretation method and device based on Web Download PDFInfo
- Publication number
- CN103956167A CN103956167A CN201410188860.2A CN201410188860A CN103956167A CN 103956167 A CN103956167 A CN 103956167A CN 201410188860 A CN201410188860 A CN 201410188860A CN 103956167 A CN103956167 A CN 103956167A
- Authority
- CN
- China
- Prior art keywords
- sign language
- web client
- participle
- voice signal
- web
- 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
Abstract
The invention discloses a visual sign language interpretation method and device based on the Web. The method includes the steps that voice signals are received from a Web client terminal; the voice signals are identified, and corresponding text information is generated; word segmentation processing is conducted on the text information, and at least one segmented word is obtained; sign language animations corresponding to the segmented words are obtained from an animation library, and a sign language animation sequence is formed; the sign language animation sequence is sent to the Web client terminal, and sign language playing is conducted by the Web client terminal according to the sign language animation sequence. Thus, people who do not understand the sign language can conveniently communicate with the deaf by inputting voice information, complex manual input is not needed, and meanwhile the demand for learning the sign language of people who do not understand the sign language can be met. In addition, due to the fact that the visual sign language interpretation method and device are based on the Web, third-party software does not need to be used, and therefore sign language translation can be conducted online at any time and any place.
Description
Technical field
The present invention relates to sign language interpreter field, particularly, relate to a kind of visual sign language interpretation method and equipment based on Web.
Background technology
In actual life, for the ease of being ignorant of crowd and deaf-mute group's communication of sign language, need to carry out sign language interpreter.But existing sign language interpretation system major part is that sign language interpreter is become to voice or word.This makes the crowd who is ignorant of sign language initiatively not mass-sended and to have exchanged with deaf-mute by voice easily, and the crowd who is ignorant of sign language has been caused to inconvenience.And deaf and dumb crowd also cannot be moved and be learned intuitively the people's information to be expressed exchanging with it by visual sign language.In addition, owing to must using sign language and this sign language interpretation system to carry out alternately, thereby this sign language interpretation system cannot meet the crowd who is ignorant of sign language and learns the demand of sign language.
Also have some sign language interpretation system can realize the two-way translation of sign language and voice, still this system is based on third party's client software.That is to say, before use, must the translation software (may also need to install corresponding database) being provided by third party be installed in client.Afterwards, carry out sign language interpreter by moving this translation software.Owing to using third party's client software, make this translation system there is very large limitation.For example, for example, in the time that the configuration of client does not meet installation requirement (, the storage space of client is little, can not meet the space requirement that related software and database are installed), cause installing this software and corresponding database, also just cannot carry out sign language interpreter.Or in the time that the client of user's use changes, user must install this third party's client software in new client, just can carry out sign language interpreter, this is very inconvenient for user.
Summary of the invention
The object of this invention is to provide a kind of convenient, visual sign language interpretation method and equipment based on Web intuitively.
To achieve these goals, the invention provides a kind of visual sign language interpretation method based on Web, the method comprises: from Web client voice signal; This voice signal is identified, and generated corresponding text message; Text information is carried out to word segmentation processing, and obtain at least one participle; From animation library, obtain the sign language animation corresponding with each participle in described at least one participle, and form sign language animation sequence; And send described sign language animation sequence to described Web client, to carry out sign language broadcasting by this Web client according to described sign language animation sequence.
The present invention also provides a kind of visual sign language interpreter equipment based on Web, and this equipment comprises: for the device from Web client voice signal; For this voice signal is identified, and generate the device of corresponding text message; For text information is carried out to word segmentation processing, and obtain the device of at least one participle; For obtain the sign language animation corresponding with each participle described at least one participle from animation library, and form the device of sign language animation sequence; And for sending described sign language animation sequence to described Web client, with the device that carries out sign language broadcasting according to described sign language animation sequence by this Web client.
By technique scheme, voice messaging can be translated into sign language information.Like this, can make to be ignorant of to such an extent that the crowd of sign language just can exchange with deaf-mute easily by input voice information, and not need loaded down with trivial details manual input, can also meet the people who is ignorant of sign language simultaneously and learn the demand of sign language.In addition, because sign language interpretation method provided by the invention and equipment are based on Web, thereby make sign language interpreter more simple and convenient.User only need to be by Web client login network address, just can carry out sign language interpreter, do not need to use third party software, also just saved the complicated process of downloading and installing third party software, avoid the requirement restriction of third party software to client, sign language interpreter can be carried out whenever and wherever possible online.
Other features and advantages of the present invention are described in detail the embodiment part subsequently.
Brief description of the drawings
Accompanying drawing is to be used to provide a further understanding of the present invention, and forms a part for instructions, is used from explanation the present invention, but is not construed as limiting the invention with embodiment one below.In the accompanying drawings:
Fig. 1 is the process flow diagram of the visual sign language interpretation method based on Web according to the embodiment of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is elaborated.Should be understood that, embodiment described herein only, for description and interpretation the present invention, is not limited to the present invention.
Fig. 1 shows the process flow diagram of the visual sign language interpretation method based on Web according to the embodiment of the present invention.As shown in Figure 1, the method can comprise: step S101, from Web client voice signal; Step S102, identifies this voice signal, and generates corresponding text message (for example, text information is based on mandarin standard); Step S103, carries out word segmentation processing to text information, and obtains at least one participle; Step S104 obtains the sign language animation corresponding with each participle in described at least one participle, and forms sign language animation sequence from animation library; And step S105, send described sign language animation sequence to described Web client, to carry out sign language broadcasting by this Web client according to described sign language animation sequence.
Described Web client can be for example browser.If user wants to carry out the application of voice-sign language interpreter, this user only need input corresponding network address on browser.Signing in to after this network address, user can come to this Web client input speech signal by voice-input devices such as microphones.Afterwards, just can realize the translation of voice-sign language by sign language interpretation method provided by the invention.
In sign language interpretation method provided by the invention, first, from Web client voice signal (, user is to the voice messaging of Web client input).Afterwards, this voice signal is identified, and generated corresponding text message.
In an embodiment of the invention, can utilize speech recognition engine to carry out the identification of voice signal.For example, this speech recognition engine can be Google's speech recognition interface (Google Speech Recognition Interface).The advantage of this speech recognition engine is that accuracy of identification is high, and call method is simple, and can support multilingual.Alternatively, this speech recognition engine can be that University of Science and Technology news fly speech recognition application programming interface interface (API).It should be noted in the discussion above that in the present invention, the speech recognition engine of other types also can be used except two examples listed above.In addition, user can also carry out to change arbitrarily easily speech recognition engine as required, or increase speech recognition engine is supported multilingual.
After voice signal is identified, can generate the text message corresponding with this voice signal.After obtaining described text message, can carry out word segmentation processing to text information.In the present invention, can adopt the known participle processing method of those skilled in the art to carry out participle to text message.After participle, can obtain at least one participle.For example, the text message obtaining through identification, for " I feel like a meal ", so, after text information is carried out to word segmentation processing, can obtain three participles, is respectively " I ", " thinking ", " having a meal ".
After obtaining at least one participle, next step obtains the sign language animation corresponding with each participle in described at least one participle, and forms sign language animation sequence from animation library.In described animation library, can store a large amount of words and the sign language animation corresponding with each word.After obtaining described at least one participle, can, according to described at least one participle, from animation library, extract the sign language animation corresponding with each participle.For example, suppose that three participles are respectively " I ", " thinking ", " having a meal ".So, can according to these three participles, from animation library, extract the sign language animation corresponding with participle " I ", the sign language animation corresponding with " thinking ", and the sign language animation corresponding with " having a meal ".After extracting corresponding sign language animation, can be according to point word order by these sign language animation composition sign language animation sequences.
Next step, be sent to described Web client by described sign language animation sequence, to carry out sign language broadcasting by this Web client according to described sign language animation sequence.
In described Web client, can use 3D player (for example, unity3d web player) to carry out sign language broadcasting.In this case, sign language interpretation method provided by the invention also comprises: before described Web client voice signal, the 3D model for playing sign language animation is loaded on to the step of described Web client.
After 3D model is loaded on to Web client, user can watch a 3D model in this Web client.For example, this 3D model can be a 3D visual human.This Web client, after receiving sign language animation sequence, can be loaded into the player on it by this sign language animation sequence.Afterwards, this player can be resolved this sign language animation sequence automatically, and controls 3D visual human action according to this sign language animation sequence.Like this, user just can watch sign language action visually by this 3D visual human.
Except utilizing 3D player to show 3D sign language broadcasting, also can realize and in Web client, show 3D sign language broadcasting by the webpage 3D technology in next generation network technology.
Thus, by technique scheme, voice messaging can be translated into sign language information.Like this, can make to be ignorant of to such an extent that the crowd of sign language just can exchange with deaf-mute easily by input voice information, and not need loaded down with trivial details manual input, can also meet the people who is ignorant of sign language simultaneously and learn the demand of sign language.In addition, because sign language interpretation method provided by the invention is based on Web, thereby make sign language interpreter more simple and convenient.User only need to pass through Web accessing server by customer end network address, just can carry out sign language interpreter, do not need to use third party software, also just saved the complicated process of downloading and installing third party software, avoid the requirement restriction of third party software to client, sign language interpreter can be carried out whenever and wherever possible online.
After the voice signal of inputting to user at Web client, this voice signal can be play by this Web client.Particularly, this Web client can comprise a voice synthetic module.After the voice signal of inputting to user at Web client, this Web client can synthesize an audio file by described voice signal by described voice synthetic module.Afterwards, this audio file transmissions to player can be play.Preferably, player is synchronously play sign language animation and described audio file.Like this, user can, in watching sign language action, can also listen to corresponding voice.By excellent both in sound and shape carry out sign language displaying, be conducive to improve and be ignorant of the effect that the crowd of sign language carries out sign language study.
In another embodiment of the present invention, described method can also comprise: send described text message to described Web client, to show described text message by this Web client.By this mode, can make user in watching sign language action, can also synchronously see word (can be called as " captions ").Like this, can provide a kind of exchange of information obtain manner for deaf-mute group more.
Of the present invention one preferred embodiment in, the step of described word segmentation processing can also comprise participle is optimized to processing, and at least one participle obtaining is the participle after optimization process.Wherein, described optimization process can comprise at least one in following operation: remove, replace, sequentially exchange.
For example, after obtaining text message, can first carry out participle to text information, afterwards, utilize the sign language vocabulary of storing in sign language dictionary, these participles are screened.The object of doing is like this from these participles, to get rid of the participle (participle that, sign language does not have in expressing) not having in sign language dictionary.After getting rid of the participle not having in sign language expression, can also replace and/or order exchange remaining participle, thereby make sign language interpreter result more meet grammer and the specification of sign language.Through after above-mentioned optimization process, can from animation library, obtain the sign language animation corresponding with each participle in described at least one participle according at least one participle obtaining after optimization process.
The present invention also provides a kind of visual sign language interpreter equipment based on Web, and this equipment can comprise: for the device from Web client voice signal; For this voice signal is identified, and generate the device of corresponding text message; For text information is carried out to word segmentation processing, and obtain the device of at least one participle; For obtain the sign language animation corresponding with each participle described at least one participle from animation library, and form the device of sign language animation sequence; And for sending described sign language animation sequence to described Web client, with the device that carries out sign language broadcasting according to described sign language animation sequence by this Web client.
Wherein, described voice signal can be by being identified with speech recognition engine.In addition, described voice signal can also, in carrying out sign language broadcasting by described Web client according to described sign language animation sequence, be play by this Web client.
In another embodiment, this equipment can also comprise: for sending described text message to described Web client, to be shown the device of described text message by this Web client.
In another embodiment, described word segmentation processing can comprise participle is optimized to processing, and at least one participle obtaining is the participle after optimization process, wherein, described optimization process comprises at least one in following operation: remove, replace, sequentially exchange.
In another embodiment, this equipment can also comprise: for before described Web client voice signal, the 3D model for playing sign language animation is loaded on to the device of described Web client.
Thus, by visual sign language interpretation method and the equipment based on Web provided by the invention, voice messaging can be translated into sign language information.Like this, can make to be ignorant of to such an extent that the crowd of sign language just can exchange with deaf-mute easily by input voice information, and not need loaded down with trivial details manual input, can also meet the people who is ignorant of sign language simultaneously and learn the demand of sign language.In addition, because sign language interpretation method provided by the invention and equipment are based on Web, thereby make sign language interpreter more simple and convenient.User only need to pass through Web accessing server by customer end network address, just can carry out sign language interpreter, do not need to use third party software, also just saved the complicated process of downloading and installing third party software, avoid the requirement restriction of third party software to client, sign language interpreter can be carried out whenever and wherever possible online.
Below describe by reference to the accompanying drawings the preferred embodiment of the present invention in detail; but; the present invention is not limited to the detail in above-mentioned embodiment; within the scope of technical conceive of the present invention; can carry out multiple simple variant to technical scheme of the present invention, these simple variant all belong to protection scope of the present invention.
It should be noted that in addition each the concrete technical characterictic described in above-mentioned embodiment, in reconcilable situation, can combine by any suitable mode.For fear of unnecessary repetition, the present invention is to the explanation no longer separately of various possible array modes.
In addition, also can carry out combination in any between various embodiment of the present invention, as long as it is without prejudice to thought of the present invention, it should be considered as content disclosed in this invention equally.
Claims (12)
1. the visual sign language interpretation method based on Web, is characterized in that, the method comprises:
From Web client voice signal;
This voice signal is identified, and generated corresponding text message;
Text information is carried out to word segmentation processing, and obtain at least one participle;
From animation library, obtain the sign language animation corresponding with each participle in described at least one participle, and form sign language animation sequence; And
Send described sign language animation sequence to described Web client, to carry out sign language broadcasting by this Web client according to described sign language animation sequence.
2. method according to claim 1, is characterized in that, described voice signal is by being identified with speech recognition engine.
3. method according to claim 1, is characterized in that, described voice signal can, in carrying out sign language broadcasting by described Web client according to described sign language animation sequence, be play by this Web client.
4. method according to claim 1, is characterized in that, the method also comprises: send described text message to described Web client, to show described text message by this Web client.
5. according to the method described in arbitrary claim in claim 1-4, it is characterized in that, described word segmentation processing comprises participle is optimized to processing, and at least one participle obtaining is the participle after optimization process, wherein, described optimization process comprises at least one in following operation: remove, replace, sequentially exchange.
6. according to the method described in arbitrary claim in claim 1-4, it is characterized in that, the method also comprises: before described Web client voice signal, the 3D model for playing sign language animation is loaded on to described Web client.
7. the visual sign language interpreter equipment based on Web, is characterized in that, this equipment comprises:
For the device from Web client voice signal;
For this voice signal is identified, and generate the device of corresponding text message;
For text information is carried out to word segmentation processing, and obtain the device of at least one participle;
For obtain the sign language animation corresponding with each participle described at least one participle from animation library, and form the device of sign language animation sequence; And
For sending described sign language animation sequence to described Web client, with the device that carries out sign language broadcasting according to described sign language animation sequence by this Web client.
8. equipment according to claim 7, is characterized in that, described voice signal is by being identified with speech recognition engine.
9. equipment according to claim 7, is characterized in that, described voice signal can, in carrying out sign language broadcasting by described Web client according to described sign language animation sequence, be play by this Web client.
10. equipment according to claim 7, is characterized in that, this equipment also comprises: for sending described text message to described Web client, to be shown the device of described text message by this Web client.
11. according to the equipment described in arbitrary claim in claim 7-10, it is characterized in that, described word segmentation processing comprises participle is optimized to processing, and at least one participle obtaining is the participle after optimization process, wherein, described optimization process comprises at least one in following operation: remove, replace, sequentially exchange.
12. according to the equipment described in arbitrary claim in claim 7-10, it is characterized in that, this equipment also comprises: for before described Web client voice signal, the 3D model for playing sign language animation is loaded on to the device of described Web client.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410188860.2A CN103956167A (en) | 2014-05-06 | 2014-05-06 | Visual sign language interpretation method and device based on Web |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410188860.2A CN103956167A (en) | 2014-05-06 | 2014-05-06 | Visual sign language interpretation method and device based on Web |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103956167A true CN103956167A (en) | 2014-07-30 |
Family
ID=51333433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410188860.2A Pending CN103956167A (en) | 2014-05-06 | 2014-05-06 | Visual sign language interpretation method and device based on Web |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103956167A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462074A (en) * | 2014-12-26 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for conducting webpage data translation and browser client side |
| WO2017161741A1 (en) * | 2016-03-23 | 2017-09-28 | 乐视控股（北京）有限公司 | Method and device for communicating information with deaf-mutes, smart terminal |
| CN107562738A (en) * | 2017-09-08 | 2018-01-09 | 合肥安华信息科技有限公司 | A kind of sign language interpretation method based on user's request |
| CN107610205A (en) * | 2017-09-20 | 2018-01-19 | 珠海金山网络游戏科技有限公司 | Webpage input audio is generated to the methods, devices and systems of mouth shape cartoon based on HTML5 |
| CN107798964A (en) * | 2017-11-24 | 2018-03-13 | 郑军 | The sign language intelligent interaction device and its exchange method of a kind of Real time identification gesture |
| CN108803871A (en) * | 2018-05-07 | 2018-11-13 | 歌尔科技有限公司 | It wears the output method of data content, device in display equipment and wears display equipment |
| CN109166409A (en) * | 2018-10-10 | 2019-01-08 | 长沙千博信息技术有限公司 | A kind of sign language conversion method and device |
| CN109409255A (en) * | 2018-10-10 | 2019-03-01 | 长沙千博信息技术有限公司 | A kind of sign language scene generating method and device |
| CN110598576A (en) * | 2019-08-21 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Sign language interaction method and device and computer medium |
| CN110890097A (en) * | 2019-11-21 | 2020-03-17 | 京东数字科技控股有限公司 | Voice processing method and device, computer storage medium and electronic equipment |
| CN111090998A (en) * | 2018-10-18 | 2020-05-01 | 北京搜狗科技发展有限公司 | Sign language conversion method and device and sign language conversion device |
| CN111857934A (en) * | 2020-07-29 | 2020-10-30 | 香港乐蜜有限公司 | Page loading method and device, electronic equipment and storage medium |
| CN113706977A (en) * | 2020-08-13 | 2021-11-26 | 苏州韵果莘莘影视科技有限公司 | Playing method and system based on intelligent sign language translation software |
-
2014
- 2014-05-06 CN CN201410188860.2A patent/CN103956167A/en active Pending
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462074A (en) * | 2014-12-26 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for conducting webpage data translation and browser client side |
| CN104462074B (en) * | 2014-12-26 | 2018-04-10 | 北京奇虎科技有限公司 | A kind of method, apparatus and browser client for carrying out web data translation |
| WO2017161741A1 (en) * | 2016-03-23 | 2017-09-28 | 乐视控股（北京）有限公司 | Method and device for communicating information with deaf-mutes, smart terminal |
| CN107562738A (en) * | 2017-09-08 | 2018-01-09 | 合肥安华信息科技有限公司 | A kind of sign language interpretation method based on user's request |
| CN107610205A (en) * | 2017-09-20 | 2018-01-19 | 珠海金山网络游戏科技有限公司 | Webpage input audio is generated to the methods, devices and systems of mouth shape cartoon based on HTML5 |
| CN107798964A (en) * | 2017-11-24 | 2018-03-13 | 郑军 | The sign language intelligent interaction device and its exchange method of a kind of Real time identification gesture |
| CN108803871A (en) * | 2018-05-07 | 2018-11-13 | 歌尔科技有限公司 | It wears the output method of data content, device in display equipment and wears display equipment |
| CN109166409A (en) * | 2018-10-10 | 2019-01-08 | 长沙千博信息技术有限公司 | A kind of sign language conversion method and device |
| CN109409255A (en) * | 2018-10-10 | 2019-03-01 | 长沙千博信息技术有限公司 | A kind of sign language scene generating method and device |
| CN111090998A (en) * | 2018-10-18 | 2020-05-01 | 北京搜狗科技发展有限公司 | Sign language conversion method and device and sign language conversion device |
| CN110598576A (en) * | 2019-08-21 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Sign language interaction method and device and computer medium |
| CN110890097A (en) * | 2019-11-21 | 2020-03-17 | 京东数字科技控股有限公司 | Voice processing method and device, computer storage medium and electronic equipment |
| CN111857934A (en) * | 2020-07-29 | 2020-10-30 | 香港乐蜜有限公司 | Page loading method and device, electronic equipment and storage medium |
| CN113706977A (en) * | 2020-08-13 | 2021-11-26 | 苏州韵果莘莘影视科技有限公司 | Playing method and system based on intelligent sign language translation software |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103956167A (en) | Visual sign language interpretation method and device based on Web | |
| US10152965B2 (en) | Learning personalized entity pronunciations | |
| US10332506B2 (en) | Computerized system and method for formatted transcription of multimedia content | |
| US9542956B1 (en) | Systems and methods for responding to human spoken audio | |
| US10950254B2 (en) | Producing comprehensible subtitles and captions for an effective group viewing experience | |
| KR20210106397A (en) | Voice conversion method, electronic device, and storage medium | |
| CN103699530A (en) | Method and equipment for inputting texts in target application according to voice input information | |
| CN109429522A (en) | Voice interactive method, apparatus and system | |
| US10824664B2 (en) | Method and apparatus for providing text push information responsive to a voice query request | |
| CN104681023A (en) | Information processing method and electronic equipment | |
| TW201921267A (en) | Method and system for generating a conversational agent by automatic paraphrase generation based on machine translation | |
| CN111261144A (en) | Voice recognition method, device, terminal and storage medium | |
| CN104407834A (en) | Message input method and device | |
| EP2747464A1 (en) | Sent message playing method, system and related device | |
| CN103546623A (en) | Method, device and equipment for sending voice information and text description information thereof | |
| CN110136715A (en) | Audio recognition method and device | |
| CN110516749A (en) | Model training method, method for processing video frequency, device, medium and calculating equipment | |
| WO2021227308A1 (en) | Video resource generation method and apparatus | |
| CN110880324A (en) | Voice data processing method and device, storage medium and electronic equipment | |
| CN110379406B (en) | Voice comment conversion method, system, medium and electronic device | |
| KR20130112221A (en) | System and method for providing conversation service connected with advertisements and contents using robot | |
| US20140129228A1 (en) | Method, System, and Relevant Devices for Playing Sent Message | |
| KR20180089242A (en) | Method, system and non-transitory computer-readable recording medium for generating dialogue contents according to output type for same at chatbot | |
| CN109213466B (en) | Court trial information display method and device | |
| CN113689854B (en) | Voice conversation method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140730 |