CN103838866B - A kind of text conversion method and device - Google Patents
A kind of text conversion method and device Download PDFInfo
- Publication number
- CN103838866B CN103838866B CN201410105981.6A CN201410105981A CN103838866B CN 103838866 B CN103838866 B CN 103838866B CN 201410105981 A CN201410105981 A CN 201410105981A CN 103838866 B CN103838866 B CN 103838866B
- Authority
- CN
- China
- Prior art keywords
- word message
- participle
- sentence
- text image
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/32—Digital ink
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
Abstract
The invention discloses a kind of text conversion method and device.The method includes：Obtain target text image；Text region is carried out to the target text image and obtains corresponding Word message；Carry out participle to the Word message, and determine the part of speech of participle, the pictorial information and/or movement locus information of correspondence participle are obtained from picture database according to the part of speech；According to the type of the sentence in the Word message, the voice messaging corresponding to the Word message is obtained from speech database；The pictorial information and/or movement locus information are exported after being adapted to the voice messaging.Technical scheme proposed by the present invention can be realized for the article of word class being converted into corresponding voice and image, increased the display format of information.
Description
Technical field
The present embodiments relate to field of computer technology, more particularly to a kind of text conversion method and device.
Background technology
Books are carry in the middle of the process of people's acquisition information and study indispensable as a kind of main tool at present
Role, such as children help typically by read books oneself understand the world, enlarge one's knowledge.But, for the age compared with
Little child, it is inaccurate or completely illiterate because reading, cause them and be difficult to the complex word class text of reading stories
Chapter, so that the content and scope of child's reading are restricted, reduces the interest of its reading.
With reaching its maturity for computer technology, electronic equipment miscellaneous（Such as learning machine, smart mobile phone, individual
Digital assistants etc.）Swarm and show, be that the aspects such as daily life, working and learning bring great convenience.It is how sharp
The article of word class is converted into into other with electronic equipment and can be seemed particularly significant by the form that child easily receives.
The content of the invention
The present invention provides a kind of text conversion method and device, so that realize for the article of word class being converted into other can be by
Voice and image that child easily receives.
In a first aspect, embodiments providing a kind of text conversion method, the method includes：
Obtain target text image；
Text region is carried out to the target text image and obtains corresponding Word message；
Carry out participle to the Word message, and determine the part of speech of participle, obtained from picture database according to the part of speech
Take the pictorial information and/or movement locus information of correspondence participle；
According to the type of the sentence in the Word message, obtain from speech database corresponding to the Word message
Voice messaging；
The pictorial information and/or movement locus information are exported after being adapted to the voice messaging.
Second aspect, the embodiment of the present invention additionally provide a kind of text conversion device, and the device includes：
Text image acquiring unit, for obtaining target text image；
Word message recognition unit, obtains corresponding word letter for Text region is carried out to the target text image
Breath；
Picture track acquiring unit, for carrying out participle to the Word message, and determines the part of speech of participle, according to described
Part of speech obtains the pictorial information and/or movement locus information of correspondence participle from picture database；
Voice messaging acquiring unit, for the type according to the sentence in the Word message, obtains from speech database
Take the voice messaging corresponding to the Word message；
Picture voice-output unit, for the pictorial information and/or movement locus information are existed with the voice messaging
Exported after being adapted to.
Technical scheme proposed by the present invention can be realized for the article of word class being converted into corresponding voice and image, increase
The display format of information.
Description of the drawings
Fig. 1 is a kind of schematic flow sheet of text conversion method that the embodiment of the present invention one is provided；
Fig. 2 is a kind of structural representation of text conversion device that the embodiment of the present invention two is provided.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that, in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is a kind of schematic flow sheet of text conversion method that the embodiment of the present invention one is provided, and the method can be by text
This conversion equipment performing, described device can be only fitted to learning machine, smart mobile phone, panel computer, personal digital assistant or
During other any one have the electronic equipment of processor, memory and display, realized by software and/or hardware.Referring to
Fig. 1, text conversion method specifically include following steps：
Step 110, acquisition target text image.
In the present embodiment, target text image is the image for including word content, can be that the books to papery enter
Row shooting obtains, or directly reads local disk related data and obtains, or acquires from respective server.
Specifically, the process of text conversion device acquisition target text image can be：Shooting is sent to picture collection device
Instruction；Receive the target text image that picture collection device shoots；Or can also be：Show text image；Reception acts on text
Input instruction on this image；The target text image in text image is determined according to input instruction.Wherein, input instruction is used
In it is determined that target text image to be converted in text image.When text conversion device is configured in point reader, input instruction
Can be that user uses the specified scope on shown text image of talking pen.
Step 120, Text region is carried out to the target text image obtain corresponding Word message.
Text conversion device is carried out to the image using the Text region algorithm of setting after target text image is got
Identification, produces corresponding Word message.Wherein, Text region algorithm can be：Line tilt correction, two-value are entered to the image first
Change, denoising, the cutting of monocase region etc. are pre-processed；Then, extract the feature of each character after cutting；Further, adopt and set
Fixed matching algorithm, each character feature for being extracted and locally stored template characteristic is compared, is recognized accordingly
As a result（That is Word message）.
Certainly those skilled in the art should be understood that Text region algorithm can also be the algorithm of other forms, for example,
After pre-processing to target text image, using this Text region algorithm of artificial neural network, directly by target text
In image, the lattice information of each character zone is sent into network model and carries out learning training, so as to identify in target text image
Word content, obtain corresponding Word message.
Step 130, participle is carried out to the Word message, and determine the part of speech of participle, according to the part of speech from picture number
According to pictorial information and/or movement locus information that correspondence participle is obtained in storehouse.
In a specific embodiment of the present embodiment, text conversion device is to obtain target text image corresponding
After Word message, participle can be carried out according to default participle technique to the Word message first；Then, further determine that each
The part of speech of participle, obtains the noun and/or the verb corresponding to the noun included in Word message；Further, from the picture
The movement locus information corresponding to the pictorial information and/or the verb corresponding to the noun is searched and is obtained in database.
Wherein, the participle technique is included but is not limited to：By word traversal, the segmenting method matched based on dictionary dictionary or knowledge based
The segmenting method of understanding.
Step 140, according to the type of the sentence in the Word message, obtain from speech database corresponding to the text
The voice messaging of word information.
In a specific embodiment of the present embodiment, after the corresponding Word message of target text image is obtained,
Text conversion device can recognize the type of each sentence in Word message according to default punctuation mark collection and/or crucial verb collection,
Wherein described type includes declarative sentence and dialogue sentence；Further, from speech database search and obtain and the statement for being identified
Voice messaging and its voice messaging matched with the dialogue sentence for being identified that sentence matches.For example, default punctuation mark
Concentration includes colon double quotation marks, and crucial verb is concentrated including " saying ", " crying out " or " asking " etc..Text conversion device is being searched sentence by sentence
When including colon double quotation marks in Word message, may recognize that the sentence between this group of punctuation mark is dialogue sentence；By text
The sentence being not included in word information between colon double quotation marks is identified as declarative sentence.Text conversion device also can found sentence by sentence
When including certain verb that crucial verb is concentrated in Word message, a corresponding behind sentence is judged to talk with sentence.
Certainly, text conversion device can also recognize each sentence in Word message in combination with punctuation mark collection and crucial verb collection
Type.
In this example, if certain sentence in identification text message is declarative sentence, search simultaneously from speech database
The voice messaging matched with the declarative sentence is obtained, for example, the voice signal of the sentence is read aloud by background sound；If identification text
The voice messaging matched with the dialogue sentence is searched and obtained to certain sentence in information from speech database to talk with during sentence,
The voice signal for for example pronouncing by the sound of correspondence personage.
Step 150, the pictorial information and/or movement locus information are carried out after being adapted to the voice messaging
Output.
In the present embodiment, text conversion device can be set up and perform according to Word message resulting during execution step 120
During step 130 between resulting pictorial information and/or resulting voice messaging when movement locus information and execution step 140
Fitting relation；It is according to this fitting relation, while showing to the pictorial information and/or movement locus information, right
The voice messaging synchronizes broadcasting.
The technical scheme that the present embodiment is proposed can be realized for the article of word class being converted into corresponding voice and image, increase
The display format of information is added.
Embodiment two
Fig. 2 is a kind of structural representation of text conversion device that the embodiment of the present invention two is provided.Referring to Fig. 2, the device
Concrete structure it is as follows：
Text image acquiring unit 210, for obtaining target text image；
Word message recognition unit 220, obtains corresponding word for carrying out Text region to the target text image
Information；
Picture track acquiring unit 230, for carrying out participle to the Word message, and determines the part of speech of participle, according to
The part of speech obtains the pictorial information and/or movement locus information of correspondence participle from picture database；
Voice messaging acquiring unit 240, for the type according to the sentence in the Word message, from speech database
Obtain the voice messaging corresponding to the Word message；
Picture voice-output unit 250, for by the pictorial information and/or movement locus information and the voice messaging
Exported after being adapted to.
Further, text image acquiring unit 210, specifically for：
Shooting instruction is sent to picture collection device；Receive the target text image that the picture collection device shoots；Or
Show text image；Reception acts on the input instruction on the text image；Determined according to the input instruction
Target text image in the text image.
Further, picture track acquiring unit 230, specifically for：
Participle is carried out according to default participle technique to the Word message；
Determine the part of speech of each participle, obtain the noun included in the Word message and/or moving corresponding to the noun
Word；
Pictorial information and/or the verb institute searched from the picture database and obtain corresponding to the noun is right
The movement locus information answered.
Further, the voice messaging acquiring unit 240, specifically for：
According to default punctuation mark collection and/or crucial verb collection, the type of each sentence in the Word message is recognized, its
Described in type include declarative sentence and dialogue sentence；
Search from speech database and obtain the voice messaging that matches with the declarative sentence for being identified and its with known
The voice messaging that the dialogue sentence not gone out matches.
Further, picture voice-output unit 250, specifically for：
According to the Word message, set up between the pictorial information and/or movement locus information and the voice messaging
Fitting relation；
According to the fitting relation, while showing to the pictorial information and/or movement locus information, to institute
State voice messaging and synchronize broadcasting.
The said goods can perform the method provided by any embodiment of the present invention, possess the corresponding functional module of execution method
And beneficial effect.
Note, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although the present invention is carried out by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
More other Equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. a kind of text conversion method, it is characterised in that include：
Obtain target text image；
Text region is carried out to the target text image and obtains corresponding Word message；
Carry out participle to the Word message, and determine the part of speech of participle, obtain right from picture database according to the part of speech
Answer the pictorial information and/or movement locus information of participle；
According to the type of the sentence in the Word message, the voice corresponding to the Word message is obtained from speech database
Information；
The pictorial information and/or movement locus information are exported after being adapted to the voice messaging.
2. text conversion method according to claim 1, it is characterised in that obtain target text image, including：
Shooting instruction is sent to picture collection device；Receive the target text image that the picture collection device shoots；Or
Show text image；Reception acts on the input instruction on the text image；According to the input instruction determines
Target text image in text image.
3. text conversion method according to claim 1, it is characterised in that carry out participle to the Word message, and really
Determine the part of speech of participle, the pictorial information and/or movement locus letter of correspondence participle are obtained from picture database according to the part of speech
Breath, including：
Participle is carried out according to default participle technique to the Word message；
Determine the part of speech of each participle, obtain noun and/or the verb corresponding to the noun included in the Word message；
Search from the picture database and obtain corresponding to the pictorial information and/or the verb corresponding to the noun
Movement locus information.
4. text conversion method according to claim 1, it is characterised in that according to the class of the sentence in the Word message
Type, obtains the voice messaging corresponding to the Word message from speech database, including：
According to default punctuation mark collection and/or crucial verb collection, the type of each sentence in the Word message, wherein institute are recognized
Stating type includes declarative sentence and dialogue sentence；
Search from speech database and obtain the voice messaging that matches with the declarative sentence for being identified and its with identified
The dialogue voice messaging that matches of sentence.
5. text conversion method according to claim 1, it is characterised in that by the pictorial information and/or movement locus
Information is exported after being adapted to the voice messaging, including：
According to the Word message, that what is set up between the pictorial information and/or movement locus information and the voice messaging is suitable
With relation；
According to the fitting relation, while showing to the pictorial information and/or movement locus information, to institute's predicate
Message breath synchronizes broadcasting.
6. a kind of text conversion device, it is characterised in that include：
Text image acquiring unit, for obtaining target text image；
Word message recognition unit, obtains corresponding Word message for carrying out Text region to the target text image；
Picture track acquiring unit, for carrying out participle to the Word message, and determines the part of speech of participle, according to the part of speech
The pictorial information and/or movement locus information of correspondence participle are obtained from picture database；
Voice messaging acquiring unit, for the type according to the sentence in the Word message, obtains right from speech database
The voice messaging of Word message described in Ying Yu；
Picture voice-output unit, for the pictorial information and/or movement locus information are being carried out with the voice messaging
Exported after adaptation.
7. text conversion device according to claim 6, it is characterised in that the text image acquiring unit, it is concrete to use
In：
Shooting instruction is sent to picture collection device；Receive the target text image that the picture collection device shoots；Or
Show text image；Reception acts on the input instruction on the text image；According to the input instruction determines
Target text image in text image.
8. text conversion device according to claim 6, it is characterised in that picture track acquiring unit, it is concrete to use
In：
Participle is carried out according to default participle technique to the Word message；
Determine the part of speech of each participle, obtain noun and/or the verb corresponding to the noun included in the Word message；
Search from the picture database and obtain corresponding to the pictorial information and/or the verb corresponding to the noun
Movement locus information.
9. text conversion method according to claim 6, it is characterised in that the voice messaging acquiring unit, it is concrete to use
In：
According to default punctuation mark collection and/or crucial verb collection, the type of each sentence in the Word message, wherein institute are recognized
Stating type includes declarative sentence and dialogue sentence；
Search from speech database and obtain the voice messaging that matches with the declarative sentence for being identified and its with identified
The dialogue voice messaging that matches of sentence.
10. text conversion device according to claim 6, it is characterised in that picture voice-output unit, specifically for：
According to the Word message, that what is set up between the pictorial information and/or movement locus information and the voice messaging is suitable
With relation；
According to the fitting relation, while showing to the pictorial information and/or movement locus information, to institute's predicate
Message breath synchronizes broadcasting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410105981.6A CN103838866B (en) | 2014-03-20 | 2014-03-20 | A kind of text conversion method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410105981.6A CN103838866B (en) | 2014-03-20 | 2014-03-20 | A kind of text conversion method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103838866A CN103838866A (en) | 2014-06-04 |
| CN103838866B true CN103838866B (en) | 2017-04-05 |
Family
ID=50802362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410105981.6A Active CN103838866B (en) | 2014-03-20 | 2014-03-20 | A kind of text conversion method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103838866B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104536570A (en) * | 2014-12-29 | 2015-04-22 | 广东小天才科技有限公司 | Information processing method and device of intelligent watch |
| CN104599670B (en) * | 2015-01-30 | 2017-12-26 | 泰顺县福田园艺玩具厂 | The audio recognition method of talking pen |
| CN105516457A (en) * | 2015-11-24 | 2016-04-20 | 小米科技有限责任公司 | Communication message processing method and apparatus |
| CN106528742A (en) * | 2016-11-04 | 2017-03-22 | 广东小天才科技有限公司 | Information query method and device |
| CN106855854A (en) * | 2016-12-29 | 2017-06-16 | 北京奇虎科技有限公司 | A kind of recognition methods of english information and device |
| CN106911959B (en) * | 2017-02-06 | 2020-01-14 | 深圳创维数字技术有限公司 | Voice picture reading method and system based on smart television |
| CN107291676B (en) * | 2017-06-20 | 2021-11-19 | 广东小天才科技有限公司 | Method for cutting off voice file, terminal equipment and computer storage medium |
| CN107748744B (en) * | 2017-10-31 | 2021-01-26 | 广东小天才科技有限公司 | Method and device for establishing drawing box knowledge base |
| CN107885827B (en) * | 2017-11-07 | 2021-06-01 | Oppo广东移动通信有限公司 | File acquisition method and device, storage medium and electronic equipment |
| CN107948405A (en) * | 2017-11-13 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | A kind of information processing method, device and terminal device |
| CN108108412A (en) * | 2017-12-12 | 2018-06-01 | 山东师范大学 | Children cognition study interactive system and method based on AI open platforms |
| CN108470067B (en) * | 2018-03-28 | 2019-03-01 | 掌阅科技股份有限公司 | E-book shows the conversion method of form, calculates equipment and computer storage medium |
| CN109766826A (en) * | 2019-01-08 | 2019-05-17 | 广东小天才科技有限公司 | A kind of method and system of automatic identification job information |
| CN111866609B (en) * | 2019-04-08 | 2022-12-13 | 百度（美国）有限责任公司 | Method and apparatus for generating video |
| CN111968424A (en) * | 2020-08-27 | 2020-11-20 | 北京大米科技有限公司 | Interactive learning method, device, system and computer storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09152883A (en) * | 1995-11-29 | 1997-06-10 | Ricoh Co Ltd | Accent phrase division position detecting method and text /voice converter |
| CN201213041Y (en) * | 2008-06-30 | 2009-03-25 | 东莞市步步高教育电子产品有限公司 | Optical click-to-read machine |
| CN101477699A (en) * | 2008-01-04 | 2009-07-08 | 白涛 | Basic programming method for converting literal sentences into corresponding animation cartoons |
| CN102479240A (en) * | 2010-11-30 | 2012-05-30 | 英业达股份有限公司 | System and method for providing example sentences according to input types |
| CN103035134A (en) * | 2012-12-10 | 2013-04-10 | 张肃 | Image touch and talk playing system and mage touch and talk playing method |
| CN103208207A (en) * | 2013-04-12 | 2013-07-17 | 北京天奇健教育科技有限公司 | Portable learning machine and using method thereof |
-
2014
- 2014-03-20 CN CN201410105981.6A patent/CN103838866B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09152883A (en) * | 1995-11-29 | 1997-06-10 | Ricoh Co Ltd | Accent phrase division position detecting method and text /voice converter |
| CN101477699A (en) * | 2008-01-04 | 2009-07-08 | 白涛 | Basic programming method for converting literal sentences into corresponding animation cartoons |
| CN201213041Y (en) * | 2008-06-30 | 2009-03-25 | 东莞市步步高教育电子产品有限公司 | Optical click-to-read machine |
| CN102479240A (en) * | 2010-11-30 | 2012-05-30 | 英业达股份有限公司 | System and method for providing example sentences according to input types |
| CN103035134A (en) * | 2012-12-10 | 2013-04-10 | 张肃 | Image touch and talk playing system and mage touch and talk playing method |
| CN103208207A (en) * | 2013-04-12 | 2013-07-17 | 北京天奇健教育科技有限公司 | Portable learning machine and using method thereof |
Non-Patent Citations (2)
| Title |
|---|
| 《盲人阅读机中图像字符识别方法的研究》;刘云曼等;《天津市生物医学工程学会学术年会2013年学术年会论文摘要》;20131231;第61页 * |
| 捷通语音设计开发智能电子书;孙騕等;《中外玩具制造》;20051031(第10期);第70页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103838866A (en) | 2014-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103838866B (en) | A kind of text conversion method and device | |
| CN106575500B (en) | Method and apparatus for synthesizing speech based on facial structure | |
| CN103761892B (en) | A kind of method of speech play paper book content and device | |
| US20190205708A1 (en) | Method and apparatus for processing information | |
| CN103955454B (en) | A kind of method and apparatus that style conversion is carried out between writings in the vernacular and the writing in classical Chinese | |
| CN113870635A (en) | Voice answering method and device | |
| CN108470188B (en) | Interaction method based on image analysis and electronic equipment | |
| Jaech et al. | Phonological pun-derstanding | |
| KR102043419B1 (en) | Speech recognition based training system and method for child language learning | |
| CN111524045A (en) | Dictation method and device | |
| Hoque et al. | Automated Bangla sign language translation system: Prospects, limitations and applications | |
| KR102222035B1 (en) | Method, terminal and program of language education for infants | |
| CN111079489B (en) | Content identification method and electronic equipment | |
| CN109473007B (en) | English natural spelling teaching method and system combining phonemes with sound side | |
| US20190304454A1 (en) | Information providing device, information providing method, and recording medium | |
| Selvaraj et al. | Enhanced portable text to speech converter for visually impaired | |
| KR102129089B1 (en) | Method, terminal and program of language education for infants | |
| Kapitanov et al. | Slovo: Russian Sign Language Dataset | |
| Bin Munir et al. | A machine learning based sign language interpretation system for communication with deaf-mute people | |
| CN111832412A (en) | Sound production training correction method and system | |
| KR102645783B1 (en) | System for providing korean education service for foreigner | |
| KR20210022288A (en) | Method for providing english education service using step-by-step expanding sentence structure unit | |
| Alam et al. | A Machine Learning Based Sign Language Interpretation System for Communication with Deaf-mute People | |
| JP6538399B2 (en) | Voice processing apparatus, voice processing method and program | |
| Bhatt et al. | Reading Assistant: a reciter in your pocket |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |