CN104517604A - English words synthesis device and method - Google Patents
English words synthesis device and method Download PDFInfo
- Publication number
- CN104517604A CN104517604A CN201310466018.6A CN201310466018A CN104517604A CN 104517604 A CN104517604 A CN 104517604A CN 201310466018 A CN201310466018 A CN 201310466018A CN 104517604 A CN104517604 A CN 104517604A
- Authority
- CN
- China
- Prior art keywords
- phonetic symbol
- module
- recognition module
- symbol table
- english words
- 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- Withdrawn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
Abstract
The invention relates to an English words synthesis device and method. The method includes: providing a phonetic symbol chart comprising phonetic symbols, archiving recognition modules to an integrating module, allowing a user to select the recognition modules corresponding to the phonetic symbols, after the user selects the recognition modules, loading and executing the selected ones of the recognition modules, reading the corresponding phonetic symbols, annotating the corresponding phonetic symbols to generate values of the phonetic symbols, and updating symbol data of the phonetic symbol chart through the annotated phonetic symbols.
Description
Technical field
The present invention relates to a kind of English synthesizer and method, especially a kind of device and method synthesized by English words and expressions.
Background technology
Display mode and voice mode are the most general two kinds of message manifestation modes of current electronic installation.In human-computer interaction interface, especially transmit message more for convenience with voice mode, add that people also increase the demand day to language learning, so also day by day urgent to speech synthesis technique demand.
But because traditional speech output method is in sentence phonation, be all pronounce by the file layout of character string, therefore naturalness is poor, the synthesis pronunciation of especially English words and phrases is obvious especially.In addition, in language data process, also need data processing personnel that the pronunciation of statement is carried out cutting by phrase so that provide material for sentence word pronunciation learning.When utilizing the conventional synthesis manner of articulation of above-mentioned manual cutting phrase, because the pronunciation of each English words is with last or end syllable, sentence can be made to pronounce not meet natural pronunciation principle, without pause when should have a pause, pause is had again when should not stop, the pronunciation gone out synthesized by causing sounds like a string long sentence, causes user to feel uninteresting, and reduces learning interest.
Summary of the invention
The present invention solves the above-mentioned technical matters existed in background technology, and proposes a kind of device synthesized by English words and expressions, produces phonetic symbol table and is sent to control center.
Technical solution of the present invention is: the present invention is a kind of device, and its special character is: this device comprises: pronunciation database; Recognition module, connects pronunciation database, is used for loading for pronunciation database and performs its phonetic symbol combination be endowed; Phonetic symbol generation module, be connected to pronunciation database, be used for producing phonetic symbol table, and continuous updating phonetic symbol table, phonetic symbol table possesses phonetic symbol combination, corresponding recognition module respectively, after recognition module is selected, pronunciation database loads and performs the recognition module be selected, and phonetic symbol generation module reads corresponding phonetic symbol, and the numerical value producing phonetic symbol is marked to phonetic symbol, re-write phonetic symbol table to upgrade phonetic symbol table.
Said apparatus comprises matching module, is connected to phonetic symbol generation module, and being used for phonetic symbol table coupling is matched data, and sends back pronunciation database.
By the method that English words and expressions synthesizes, run on device, its special character is: the method comprises the following step:
1) the phonetic symbol table providing phonetic symbol to combine;
2) recognition module is converged whole in integrate module, choose recognition module for user, and recognition module corresponding phonetic symbol respectively;
3) load and perform the recognition module be selected;
4) read corresponding phonetic symbol, and the numerical value producing phonetic symbol is marked to phonetic symbol;
5) phonetic symbol data in phonetic symbol table is upgraded with the phonetic symbol after being marked.
Said method comprises step 6), and continuous wait recognition module is selected, and to load and to perform the recognition module be selected, and upgrades phonetic symbol table.
Said method also comprises step 7) and mates phonetic symbol table, saves as matched data.
Accompanying drawing explanation
Fig. 1 is the system block diagrams of apparatus of the present invention;
Fig. 2 is the inventive method process flow diagram;
Embodiment
See Fig. 1, apparatus of the present invention comprise pronunciation database 110, recognition module 112, display module 120, load module 130, phonetic symbol generation module 140, matching module 150.
Pronunciation database 110 is mainly the system core of end device, is used for driving each module to run, and accepts external data or instruction input.Recognition module 112 is connected to pronunciation database, is used for loading for pronunciation database 110 and performing its combination be endowed.
Display module 120 is connected to pronunciation database 110, and recognition module 112 can be converged whole in integrate module by pronunciation database 110, transfers to display module 120, display system master catalogue picture.
Load module 130 is used for inputting instructions for user, required recognition module 112 is chosen from system master catalog picture, load further for pronunciation database 110 and performed, the execution result of recognition module 112 is shown in display module 120, and user can input instruction further by load module 130 and recognition module 112 is interactive.
Phonetic symbol generation module is connected to pronunciation database, and 140 are used for producing phonetic symbol table, and continuous updating phonetic symbol table.This phonetic symbol table through initialization, produces the phonetic symbol possessing initial value when first time loads, the corresponding recognition module 112 of each phonetic symbol.After user chooses recognition module 112 by load module 110, pronunciation database 110 is except loading chosen recognition module, and outside being performed, pronunciation database 110 also can be sent to phonetic symbol generation module 140 by choosing result simultaneously, now phonetic symbol generation module 140 can read corresponding phonetic symbol, and the numerical value producing this phonetic symbol is marked to phonetic symbol, finally re-write phonetic symbol table again and upgrade phonetic symbol table.
Matching module 150 is connected to phonetic symbol generation module 140, and being used for phonetic symbol table coupling is matched data.After phonetic symbol table completes renewal, phonetic symbol table is sent to matching module 150 by phonetic symbol generation module 140, and matching module 150 pairs of phonetic symbol tables mate.Pronunciation database 110 can assign matching algorithm and coupling password parameter to matching module 150 further.Matched data finally sends back pronunciation database 110 again, externally transmits further for pronunciation database 110.
See Fig. 2, the method method of operation is described as follows:
Phonetic symbol generation module 140 first can produce the blank phonetic symbol table not comprising phonetic symbol data, then each recognition module is distributed to the initial value (S220) of phonetic symbol, and each phonetic symbol and corresponding recognition module 112 thereof are write in phonetic symbol table, complete the initialization (S222) of phonetic symbol table.
Then whole device enters using state, recognition module 112 is converged whole in integrate module by pronunciation database 110, by display module 120 display system master catalogue picture (S230).
User's load module 130 chooses recognition module 112, and pronunciation database 110 can load and perform the recognition module 112 be selected.This is chosen result simultaneously and be sent to phonetic symbol generation module 140, phonetic symbol generation module 140 is triggered, now phonetic symbol generation module 140 can read corresponding phonetic symbol, and marks to phonetic symbol the numerical value producing phonetic symbol.
Then phonetic symbol table is sent to matching module 150, and matching module 150 pairs of phonetic symbol tables carry out coupling and preserve (S270).
After phonetic symbol table upgrades and terminates, phonetic symbol generation module 140 just enters waiting status, waits for trigger event (user chooses recognition module 112) next time, carries out phonetic symbol table next time and upgrades (S280).
Claims (7)
1. by the device that English words and expressions synthesizes, produce phonetic symbol table and be sent to control center, analyze the user learning custom using this device, it is characterized in that: this device comprises: pronunciation database; Recognition module, connects pronunciation database, is used for loading for pronunciation database and performing its combination be endowed; Phonetic symbol generation module, be connected to pronunciation database, be used for producing phonetic symbol table, and continuous updating phonetic symbol table, phonetic symbol table possesses phonetic symbol, corresponding recognition module respectively, after recognition module is selected, pronunciation database loads and performs the recognition module be selected, and phonetic symbol generation module reads corresponding phonetic symbol, and the numerical value producing phonetic symbol is marked to phonetic symbol, re-write phonetic symbol table to upgrade phonetic symbol table.
2. the device synthesized by English words and expressions according to claim 1, is characterized in that: described device comprises display module, is connected to pronunciation database, is used at system master catalog picture display integrate module.
3. the device synthesized by English words and expressions according to claim 1, is characterized in that: described phonetic symbol table through initialization, produces the phonetic symbol possessing initial value when first time loads, the corresponding recognition module of each phonetic symbol.
4. the device synthesized by English words and expressions according to claim 1, is characterized in that: described device comprises matching module, is connected to phonetic symbol generation module, and being used for phonetic symbol table coupling is matched data, and sends back pronunciation database.
5. by the method that English words and expressions synthesizes, run on device, it is characterized in that: the method comprises the following step:
1) the phonetic symbol table possessing phonetic symbol is provided;
2) recognition module is converged whole in integrate module, choose recognition module for user, and recognition module corresponding phonetic symbol respectively;
3) load and perform the recognition module be selected;
4) read corresponding phonetic symbol, and the numerical value producing phonetic symbol is marked to phonetic symbol;
5) phonetic symbol data in phonetic symbol table is upgraded with the phonetic symbol after being marked.
6. method of being synthesized by English words and expressions according to claim 5, is characterized in that: described method comprises step 6): continuous wait recognition module is selected, and to load and to perform the recognition module be selected, and upgrades phonetic symbol table.
7. method of being synthesized by English words and expressions according to claim 5, is characterized in that: described method also comprises step 7): mate phonetic symbol table, save as matched data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310466018.6A CN104517604A (en) | 2013-09-29 | 2013-09-29 | English words synthesis device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310466018.6A CN104517604A (en) | 2013-09-29 | 2013-09-29 | English words synthesis device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104517604A true CN104517604A (en) | 2015-04-15 |
Family
ID=52792810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310466018.6A Withdrawn CN104517604A (en) | 2013-09-29 | 2013-09-29 | English words synthesis device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104517604A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI622029B (en) * | 2017-09-15 | 2018-04-21 | 驊鉅數位科技有限公司 | Interactive language learning system with pronunciation recognition |
-
2013
- 2013-09-29 CN CN201310466018.6A patent/CN104517604A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI622029B (en) * | 2017-09-15 | 2018-04-21 | 驊鉅數位科技有限公司 | Interactive language learning system with pronunciation recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kisler et al. | Signal processing via web services: the use case WebMAUS | |
| Prahallad et al. | The IIIT-H Indic speech databases. | |
| US8996384B2 (en) | Transforming components of a web page to voice prompts | |
| CA2818004C (en) | Text conversion and representation system | |
| US11488577B2 (en) | Training method and apparatus for a speech synthesis model, and storage medium | |
| WO2021189984A1 (en) | Speech synthesis method and apparatus, and device and computer-readable storage medium | |
| CN105845125A (en) | Speech synthesis method and speech synthesis device | |
| CN103366731A (en) | Text to speech (TTS) method and system | |
| CN103250148A (en) | Methods and systems for transcribing or transliterating to an iconophonological orthography | |
| CN105225659A (en) | A kind of instruction type Voice command pronunciation dictionary auxiliary generating method | |
| CN104239007A (en) | Method for natural persons speaking Chinese to remotely control lamp through voice | |
| CN104235998A (en) | Method for non-specified people to remotely control intelligent air conditioner through Chinese phonetic symbols | |
| CN103854648A (en) | Chinese and foreign language voiced image data bidirectional reversible voice converting and subtitle labeling method | |
| US9087512B2 (en) | Speech synthesis method and apparatus for electronic system | |
| CN104517604A (en) | English words synthesis device and method | |
| CN103853705A (en) | Real-time voice subtitle translation method of Chinese voice and foreign language voice of computer | |
| Schauffler et al. | » textklang «–Towards a Multi-Modal Exploration Platform for German Poetry | |
| CN104235042B (en) | The method of Chinese speech remote control electric fan | |
| Zhiyong et al. | A unified framework for multilingual text-to-speech synthesis with SSML specification as interface | |
| TW201537372A (en) | Action designing device and action designing program | |
| CN108228191B (en) | Grammar compiling system and grammar compiling method | |
| Isaac et al. | Improving Automatic Speech Recognition for Mobile Learning of Mathematics Through Incremental Parsing. | |
| CN104698990A (en) | Method of remotely controlling robot by non-specific person foreign language speech | |
| CN104698988A (en) | Controller device for robot remotely controlled by non-specific person foreign language speech | |
| CN104516871A (en) | Word and context combining test method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C04 | Withdrawal of patent application after publication (patent law 2001) | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20150415 |