CN104809923A - Self-complied and self-guided method and system for generating intelligent voice communication - Google Patents
Self-complied and self-guided method and system for generating intelligent voice communication Download PDFInfo
- Publication number
- CN104809923A CN104809923A CN201510241874.0A CN201510241874A CN104809923A CN 104809923 A CN104809923 A CN 104809923A CN 201510241874 A CN201510241874 A CN 201510241874A CN 104809923 A CN104809923 A CN 104809923A
- Authority
- CN
- China
- Prior art keywords
- lines
- works
- role
- dialogue
- generation method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/04—Electrically-operated educational appliances with audible presentation of the material to be studied
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
Abstract
The invention discloses a self-complied and self-guided method and system for generating intelligent voice communication. The method comprises the following steps: a) naming works; b) setting or adding a plurality of characters, and setting different voice characteristics for the different characters; c) adding words, and setting the sequence of the words; d) carrying out semantic analysis, identifying the words, automatically prompting and correcting error words, and generating the voice communication; e) previewing the works of the voice communication, and adjusting the voice characteristics of each character when speaking different words according to the content and context of the words by an operator; f) generating the works of the voice communication. Compared with the prior art, the system can generate multi-character voice communication with full emotion by utilizing the words in a text form, the error words can be automatically corrected, and the voice characteristics of character communication are adjusted, so that the generated voice communication are vivid and interesting and are more close to life.
Description
Technical field
The present invention relates to speech dialogue system field, particularly relate to a kind of Intelligent voice dialog write and directed himself and generate method and system.
Background technology
In foreign language teaching, usually need to use situational dialogues to help the application that student understands foreign language statement, for English teaching, the text in English teaching material comes in the mode of many people dialogue implication and the application scenario that guiding student understands english statement usually.But the content in existing English teaching material textbook is more single, and be text description mostly, more dull uninteresting, the learning initiative of student is lower, and learning efficiency is low.
In order to improve the efficiency of teaching of English, existing teaching can utilize speech dialogue system to write and direct himself dialogue, student and teacher oneself can conceive more exquisite dialogue, thus expand the ability of practice of Students ' Learning foreign language, motivate students' interest in learning, be convenient under class, utilize network to strengthen the study of English.
But, existing speech dialogue system generally adopts the mode of recorded speech to form English dialogue, and the voice of recording form voice dialogue after noise reduction process, if be provided with multiple role in the voice dialogue recorded, then need multiple corresponding roles recording on the scene simultaneously, should use very inconvenient.
Therefore, be necessary to provide a kind of new Intelligent voice dialog generation method to solve the problems referred to above.
Summary of the invention
A kind of Intelligent voice dialog of the polygonal look voice dialogue that can write and direct himself is the object of the present invention is to provide to generate method and system.
To achieve these goals, the technical solution adopted in the present invention is as follows:
A kind of Intelligent voice dialog generation method write and directed himself, comprises the following steps:
A) works are named;
B) set or add multiple role, for different role arranges different sound properties;
C) add lines, and the sequencing of described lines is set;
D) semantic analysis, identifies lines, automatic-prompting lines of correcting a mistake, and generates voice dialogue;
E) preview voice dialogue works, operator, according to lines content and linguistic context, adjusts the sound property of each role when telling about different lines;
F) voice dialogue works are generated.
Preferably, in step b) described in sound property comprise in tone, tone color, volume, word speed and rhythm one or more.
Preferably, a) and between step b) following steps are increased in step: a1) for works interpolation word scene description is or/and sound scenery describes.
Preferably, in step c) in give described word scene description or/and sound scenery describes direct typing scene lines or input scene lines text.
Preferably, in step c), lines or input dialogue lines text is talked with directly to different role typing.
Preferably, in step d) in identify after all lines, whether the entirety semantic judgment part lines according to all lines have phonetic or radicals by which characters are arranged in traditional Chinese dictionaries mistake, if judge wrong, verify check lines, and the lines before and after display corrigendum.
Preferably, steps d) in display corrigendum before and after lines after, operator judges that whether the lines before correcting are wrong, if errorless operator selects to determine the lines before correcting, if wrong, operator judges that whether the lines after correcting are wrong, if errorless operator selects to determine the lines after correcting, if wrong operator corrects lines voluntarily.
Preferably, described role comprises one or more in boy, young girl, adult male population, adult women, old man and old woman.
The present invention also provides a kind of voice dialogue generation system applying described Intelligent voice dialog generation method, comprising:
Role adds and setting unit, presets role or immediately adds role, for different role arranges different sound properties, described sound property comprise in tone, tone color, volume, word speed and rhythm one or more;
Works name unit is the name of works theme, and is works coupling at least two roles;
Lines adding device, for works add role's lines or/and background lines;
Semantic analysis unit, identifies lines, automatic-prompting lines of correcting a mistake, and generates voice dialogue;
Works preview unit, preview voice dialogue, operator, according to lines content and linguistic context, adjusts the sound property of each role when telling about different lines.
Compared with prior art, the beneficial effect that the Intelligent voice dialog that the present invention can write and direct himself generates method and system is: the present invention can utilize the lines of written form to generate the polygonal look voice dialogue with full mood, and lines of can automatically correcting a mistake, the sound property of adjustment part dialog, make the voice dialogue vivid and interesting of generation, more closeness to life.
Accompanying drawing explanation
Fig. 1 is the implementation step figure of Intelligent voice dialog generation method of the present invention.
Embodiment
Below in conjunction with specific embodiment, the present invention is described further.
Refer to shown in Fig. 1, the Intelligent voice dialog generation method that the present invention can write and direct himself comprises the following steps:
A) works are named;
A1) for works add word scene description or/and sound scenery describes,
B) set or add multiple role, described role comprises boy, young girl, adult male population, adult women, old man and old woman, for different role arranges different sound properties, described sound property comprise in tone, tone color, volume, word speed and rhythm one or more;
C) lines are added, to described word scene description or/and sound scenery describes direct typing scene lines or input scene lines text, to different role typing dialogue lines or input dialogue lines text, and the sequencing of described scene lines (text) and dialogue lines (text) is set;
D) semantic analysis, identifies lines, and whether the entirety semantic judgment part lines according to all lines have phonetic or radicals by which characters are arranged in traditional Chinese dictionaries mistake, if judge wrong, and verify check lines, and the lines before and after display corrigendum; Operator judges that whether the lines before correcting are wrong, if errorless operator selects to determine the lines before correcting, if wrong, operator judges that whether the lines after correcting are wrong, if errorless operator selects to determine the lines after correcting, if wrong operator corrects lines voluntarily; Analysis station word justice generates voice dialogue;
E) preview voice dialogue works, operator, according to lines content and linguistic context, adjusts the sound property of each role when telling about different lines;
F) voice dialogue works are generated.
The present invention also provides a kind of voice dialogue generation system applying described Intelligent voice dialog generation method, comprising:
Role adds and setting unit, presets role or immediately adds role, for different role arranges different sound properties, described sound property comprise in tone, tone color, volume, word speed and rhythm one or more;
Works name unit is the name of works theme, and is works coupling at least two roles;
Lines adding device, for works add role's lines or/and background lines;
Semantic analysis unit, identifies lines, automatic-prompting lines of correcting a mistake, and generates voice dialogue;
Works preview unit, preview voice dialogue, operator, according to lines content and linguistic context, adjusts the sound property of each role when telling about different lines.
In the present invention, described role can also classify again according to the difference of its character color, for old man, healthy old man and seriously ill old man in tone and rhythm of speaking etc. on have any different, the word speed of the old man that personality is more irritable is faster than the word speed of mild old man.
Described scene lines and lines text can manually instant typings, also can pre-deposit in document and form scene lines text and dialogue lines text, described scene lines text and dialogue lines text adopt the txt form easily identified, when embody rule, after designing according to user's needs, also the forms such as doc can be adopted.
In semantic analysis step, system can utilize sound bank to mate, sound bank takes from the user speech of magnanimity, and by the modeling of system science, role's sound of all ages and classes, personality characteristic can be mated, according to the text of operator's input, analyze the semanteme in text, and give suitable speech intonation, make the voice dialogue vivid and interesting of generation, closeness to life more.In addition, system can also be corrected the lines of the other radicals by which characters are arranged in traditional Chinese dictionaries mistake of misspelling or limit, improves the accuracy of voice dialogue.
In preview voice dialogue works step, operator can according to lines content and linguistic context, the suitably sound property of each role of adjustment when telling about different lines.Such as in case of emergency, the volume of certain lines of same role and tone etc. are more big changes relative to other lines, word speed can be accelerated, volume can increase, if automatically change role when system intelligence sounding to should the sound property of sentence lines, or sound property is changed little, situational dialogues will be caused untrue, the mode of artificial adjustment at this moment just can be taked to solve this problem.
In interpolation lines step, can typing word scene description or/and sound scenery describe lines, the background that explanation dialogue occurs, such as two classmate meet generation situational dialogues at the zoo, the relation of two people and place of meeting can be handed in word scene or sound scenery, make audience be easier to understand conversation content.When embody rule, can also, as required for voice dialogue arranges background picture, picture, sound and word be combined together, increase the vividness of voice dialogue.
In sum, the present invention is simple to operate, and a few step of easy manipulation can create voice dialogue works; Advanced technology, the linguistic context sense of reality is comparatively strong, complete to make quality high; Extensibility is high, may be used in the teaching of different foreign language.
Schematically above be described the present invention and embodiment thereof, this description does not have restricted, and also just one of the embodiments of the present invention shown in accompanying drawing, actual structure is not limited thereto.So, if those of ordinary skill in the art enlightens by it, when not departing from the invention aim, designing the frame mode similar to this technical scheme and embodiment without creationary, all should protection scope of the present invention be belonged to.
Claims (9)
1. the Intelligent voice dialog generation method that can write and direct himself, is characterized in that, comprise the following steps:
A) works are named;
B) set or add multiple role, for different role arranges different sound properties;
C) add lines, and the sequencing of described lines is set;
D) semantic analysis, identifies lines, automatic-prompting lines of correcting a mistake, and generates voice dialogue;
E) preview voice dialogue works, operator, according to lines content and linguistic context, adjusts the sound property of each role when telling about different lines;
F) voice dialogue works are generated.
2. the Intelligent voice dialog generation method that can write and direct himself as claimed in claim 1, is characterized in that, in step b) described in sound property comprise in tone, tone color, volume, word speed and rhythm one or more.
3. the Intelligent voice dialog generation method that can write and direct himself as claimed in claim 1, is characterized in that, a) and between step b) increase following steps in step: a1) for works interpolation word scene description is or/and sound scenery describes.
4. the Intelligent voice dialog generation method that can write and direct himself as claimed in claim 3, is characterized in that, in step c) in give described word scene description or/and sound scenery describes direct typing scene lines or input scene lines text.
5. the Intelligent voice dialog generation method that can write and direct himself as claimed in claim 1, is characterized in that, directly to different role typing dialogue lines or input dialogue lines text in step c).
6. the Intelligent voice dialog generation method that can write and direct himself as claimed in claim 1, it is characterized in that, in step d) in identify after all lines, whether the entirety semantic judgment part lines according to all lines have phonetic or radicals by which characters are arranged in traditional Chinese dictionaries mistake, if judge wrong, verify check lines, and the lines before and after display corrigendum.
7. the Intelligent voice dialog generation method that can write and direct himself as claimed in claim 6, it is characterized in that, steps d) in display corrigendum before and after lines after, operator judges that whether the lines before correcting are wrong, if errorless operator selects to determine the lines before correcting, if wrong, operator judges that whether the lines after correcting are wrong, if errorless operator selects to determine the lines after correcting, if wrong operator corrects lines voluntarily.
8. the Intelligent voice dialog generation method that can write and direct himself as claimed in claim 1, is characterized in that, described role comprise in boy, young girl, adult male population, adult women, old man and old woman one or more.
9. application as arbitrary in claim 1 to 8 as described in the voice dialogue generation system of Intelligent voice dialog generation method, it is characterized in that, comprising:
Role adds and setting unit, presets role or immediately adds role, for different role arranges different sound properties, described sound property comprise in tone, tone color, volume, word speed and rhythm one or more;
Works name unit is the name of works theme, and is works coupling at least two roles;
Lines adding device, for works add role's lines or/and background lines;
Semantic analysis unit, identifies lines, automatic-prompting lines of correcting a mistake, and generates voice dialogue;
Works preview unit, preview voice dialogue, operator, according to lines content and linguistic context, adjusts the sound property of each role when telling about different lines.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510241874.0A CN104809923A (en) | 2015-05-13 | 2015-05-13 | Self-complied and self-guided method and system for generating intelligent voice communication |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510241874.0A CN104809923A (en) | 2015-05-13 | 2015-05-13 | Self-complied and self-guided method and system for generating intelligent voice communication |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104809923A true CN104809923A (en) | 2015-07-29 |
Family
ID=53694718
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510241874.0A Pending CN104809923A (en) | 2015-05-13 | 2015-05-13 | Self-complied and self-guided method and system for generating intelligent voice communication |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104809923A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106846938A (en) * | 2017-04-07 | 2017-06-13 | 苏州清睿教育科技股份有限公司 | A kind of intelligent human-computer dialogue exercise system and courseware making methods |
CN107396177A (en) * | 2017-08-28 | 2017-11-24 | 北京小米移动软件有限公司 | Video broadcasting method, device and storage medium |
CN108091321A (en) * | 2017-11-06 | 2018-05-29 | 芋头科技(杭州)有限公司 | A kind of phoneme synthesizing method |
CN110459200A (en) * | 2019-07-05 | 2019-11-15 | 深圳壹账通智能科技有限公司 | Phoneme synthesizing method, device, computer equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2002001404A2 (en) * | 2000-06-27 | 2002-01-03 | Text Analysis International, Inc. | Automated generation of text analysis systems |
CN1704923A (en) * | 2004-05-27 | 2005-12-07 | 杭州草莓资讯有限公司 | English learning system through synchronous multiple persons online situational role playing |
CN101247481A (en) * | 2007-02-16 | 2008-08-20 | 李西峙 | System and method for producing and playing real-time three-dimensional movie/game based on role play |
CN102693729A (en) * | 2012-05-15 | 2012-09-26 | 北京奥信通科技发展有限公司 | Customized voice reading method, system, and terminal possessing the system |
CN103117057A (en) * | 2012-12-27 | 2013-05-22 | 安徽科大讯飞信息科技股份有限公司 | Application method of special human voice synthesis technique in mobile phone cartoon dubbing |
CN103871407A (en) * | 2012-12-07 | 2014-06-18 | 浦项工科大学校产学协力团 | Method and apparatus for correcting speech recognition error |
CN104415554A (en) * | 2013-08-23 | 2015-03-18 | 朱江 | Customized role-playing method of intelligent interactive toy storyboard |
-
2015
- 2015-05-13 CN CN201510241874.0A patent/CN104809923A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2002001404A2 (en) * | 2000-06-27 | 2002-01-03 | Text Analysis International, Inc. | Automated generation of text analysis systems |
CN1704923A (en) * | 2004-05-27 | 2005-12-07 | 杭州草莓资讯有限公司 | English learning system through synchronous multiple persons online situational role playing |
CN101247481A (en) * | 2007-02-16 | 2008-08-20 | 李西峙 | System and method for producing and playing real-time three-dimensional movie/game based on role play |
CN102693729A (en) * | 2012-05-15 | 2012-09-26 | 北京奥信通科技发展有限公司 | Customized voice reading method, system, and terminal possessing the system |
CN103871407A (en) * | 2012-12-07 | 2014-06-18 | 浦项工科大学校产学协力团 | Method and apparatus for correcting speech recognition error |
CN103117057A (en) * | 2012-12-27 | 2013-05-22 | 安徽科大讯飞信息科技股份有限公司 | Application method of special human voice synthesis technique in mobile phone cartoon dubbing |
CN104415554A (en) * | 2013-08-23 | 2015-03-18 | 朱江 | Customized role-playing method of intelligent interactive toy storyboard |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106846938A (en) * | 2017-04-07 | 2017-06-13 | 苏州清睿教育科技股份有限公司 | A kind of intelligent human-computer dialogue exercise system and courseware making methods |
CN107396177A (en) * | 2017-08-28 | 2017-11-24 | 北京小米移动软件有限公司 | Video broadcasting method, device and storage medium |
CN108091321A (en) * | 2017-11-06 | 2018-05-29 | 芋头科技(杭州)有限公司 | A kind of phoneme synthesizing method |
CN108091321B (en) * | 2017-11-06 | 2021-07-16 | 芋头科技(杭州)有限公司 | Speech synthesis method |
CN110459200A (en) * | 2019-07-05 | 2019-11-15 | 深圳壹账通智能科技有限公司 | Phoneme synthesizing method, device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Iyyer et al. | Adversarial example generation with syntactically controlled paraphrase networks | |
KR102423302B1 (en) | Apparatus and method for calculating acoustic score in speech recognition, apparatus and method for learning acoustic model | |
WO2018153213A1 (en) | Multi-language hybrid speech recognition method | |
US8818926B2 (en) | Method for personalizing chat bots | |
CN110797010A (en) | Question-answer scoring method, device, equipment and storage medium based on artificial intelligence | |
CA3011397A1 (en) | Natural expression processing method, processing and response method, device and system | |
CN103000052A (en) | Man-machine interactive spoken dialogue system and realizing method thereof | |
CN106803422A (en) | A kind of language model re-evaluation method based on memory network in short-term long | |
CN104809923A (en) | Self-complied and self-guided method and system for generating intelligent voice communication | |
KR20160008949A (en) | Apparatus and method for foreign language learning based on spoken dialogue | |
KR20190134053A (en) | Method of learning emotional conversations based on sequence-to-sequence neural network for psychological counseling | |
CN114064865A (en) | Detecting lexical skill levels and correcting misalignment in remote interactions | |
KR20220083987A (en) | Voice synthesizing method, device, electronic equipment and storage medium | |
CN103810993B (en) | Text phonetic notation method and device | |
Yu et al. | The BURCHAK corpus: A challenge data set for interactive learning of visually grounded word meanings | |
CN111968646A (en) | Voice recognition method and device | |
Ashihara et al. | SpeechGLUE: How well can self-supervised speech models capture linguistic knowledge? | |
KR102395702B1 (en) | Method for providing english education service using step-by-step expanding sentence structure unit | |
KR102384165B1 (en) | Real-time two-way communication method and system through video and audio data transmission and reception in virtual space | |
CN110348010B (en) | Synonymous phrase acquisition method and apparatus | |
KR100979561B1 (en) | Interactive language learning apparatus | |
CN111191451A (en) | Chinese sentence simplification method and device | |
CN112528680A (en) | Corpus expansion method and system | |
Kuhn et al. | Measuring the accuracy of automatic speech recognition solutions | |
CN110782514A (en) | Mouth shape switching rendering system and method based on unreal engine |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
EXSB | Decision made by sipo to initiate substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: Suzhou City, Jiangsu Province, Suzhou Industrial Park 215000 Xinghu Street No. 328 Creative Industry Park 16-A301 unit Applicant after: Suzhou Rui Rui education Polytron Technologies Inc Address before: Suzhou City, Jiangsu Province, Suzhou Industrial Park 215000 Xinghu Street No. 328 Creative Industry Park 16-A301 unit Applicant before: Suzhou Qing Rui Information Technology Co., Ltd |
|
COR | Change of bibliographic data | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150729 |