CN203386472U - Character voice changer - Google Patents
Character voice changer Download PDFInfo
- Publication number
- CN203386472U CN203386472U CN201320217640.9U CN201320217640U CN203386472U CN 203386472 U CN203386472 U CN 203386472U CN 201320217640 U CN201320217640 U CN 201320217640U CN 203386472 U CN203386472 U CN 203386472U
- Authority
- CN
- China
- Prior art keywords
- voice
- module
- sound
- individual character
- changing device
- 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.)
- Expired - Fee Related
Links
Images
Abstract
A character voice changer includes a voice acquisition module (1), a voice library construction module (2), a character voice library module (3), a voice recognition module (4), a voice synthesis module (5) and a voice output module (6). Based on the modules, the voice changer can construct a character voice library of different people first, then change the acquired voice information into voice information with people' characters in the character voice library, and output the changed voice information. The character voice changer has strong performance of entertainment and function, can be applied to toys, character repeaters and the like; and the character voice changer can also be made into a chip to be installed to a mobile phone and other communication equipment, so as to enhance the functions of the mobile phone and the other communication equipment.
Description
Technical field
The utility model relates to a kind of voice sound changing device, relates in particular to a kind of individual character voice sound changing device.
Background technology
At present, phonetic synthesis and speech recognition technology are ripe gradually, and phonetic synthesis and speech recognition product and application also increase gradually.But current voice change of voice technology and product application are also more rare.Mostly current voice change of voice product, be to carry out the change of some phonetic feature on original speech basic, makes to change rear voice different with original sound, thereby reach the effect of the voice change of voice, but the voice change of voice can't be become to the individual character voice of certain particular person.
Summary of the invention
The purpose of this utility model is that the existing voice change of voice product of solution is less, and voice can't be changed into to the problem of certain particular person voice, by conjunction with modules such as phonetic synthesis and speech recognitions, provides a kind of individual character voice sound changing device.
This device can, by recording the voice of speaker, generate the individual character sound bank of corresponding speaker; Then as required, can carry out the change of voice of individual character voice to any voice that receive, change the voice with individual character sound bank speaker characteristics into, be exported.
The individual character voice sound changing device that the utility model provides comprises: voice acquisition module (1), and the sound storehouse builds module (2), individual character sound bank module (3), sound identification module (4), voice synthetic module (5) and voice output module (6); Described voice acquisition module (1) connects respectively the sound storehouse and builds module (2) and sound identification module (4), and sound identification module (4) connects voice synthetic module (5) and voice output module (6) successively; The sound storehouse builds module (2) and connects individual character sound bank module (3), and individual character sound bank module (3) connects voice synthetic module (5) simultaneously.
Described voice acquisition module is for gathering voice messaging.Voice acquisition module can adopt the audio collection chip to realize.The voice messaging collected as required, can carry out the sound bank structure, or carries out the change of voice of individual character voice output.
Described sound storehouse builds module for the speech data of speaker is processed, and obtains the speaker speech elementary cell that comprises the pitch period markup information, and structure speaker individual character sound bank is stored in individual character sound bank module.Language data process to speaker mainly comprises syllabification, the division of pure and impure sound and pitch period mark etc.The function that the sound storehouse builds module can realize by pronounciation processing chip.
Described individual character sound bank module is for storing the memory module in different speaker speech storehouse, can realizing by groups of memory chips.Can store the sound bank of a plurality of speaker in individual character sound bank module, the individual character sound bank of each speaker is to consist of the speaker speech elementary cell that comprises the pitch period markup information, can carry out phonetic synthesis by the PSOLA chipspeech.
Described sound identification module, for voice messaging, identify fast its text message, and text information passed to voice synthetic module.This module can realize by voice recognition chip.
Described voice synthetic module, for text message, utilize the speaker speech information of individual character sound bank, generates the voice messaging with these individual character sound bank speaker characteristics by the PSOLA algorithm, and be transferred to the voice output module.This module can realize by the PSOLA chipspeech.
Described voice output module, exported for the voice messaging by after the change of voice.Voice output module (6) is the audio frequency pio chip.
Advantage of the present utility model and beneficial effect:
User of the present utility model, can be own or invite friend to record the individual character sound bank, then just can simulate the voice of individual character sound bank speaker, has well recreational.Can also can make chip for various application such as toy, individual character language repeaters, be arranged on the communication apparatus such as mobile phone, functional to increase it.
The accompanying drawing explanation
Fig. 1 is general structure schematic diagram of the present utility model.
Fig. 2 is the structural representation that the utility model builds speaker individual character sound bank.
Fig. 3 is the structural representation that the utility model carries out the change of voice of individual character voice to the input voice.
Below in conjunction with drawings and Examples, the utility model is further illustrated.
Embodiment
Embodiment
As shown in Figure 1, general structure schematic diagram for a kind of individual character voice of the utility model sound changing device, this device comprises voice acquisition module (1), the sound storehouse builds module (2), individual character sound bank module (3), sound identification module (4), voice synthetic module (5) and voice output module (6).
Described voice acquisition module (1) can realize by the audio collection chip, the sound storehouse builds module (2) and can realize by pronounciation processing chip, individual character sound bank module (3) can realize by groups of memory chips, sound identification module (4) can be realized by voice recognition chip, voice synthetic module (5) can realize by chipspeech, and voice output module (6) can realize by the audio frequency pio chip.
Described voice acquisition module (1) connects respectively the sound storehouse and builds module (2) and sound identification module (4), and sound identification module (4) connects voice synthetic module (5) and voice output module (6) successively; The sound storehouse builds module (2) and connects individual character sound bank module (3), and individual character sound bank module (3) connects voice synthetic module (5) simultaneously.
As shown in Figure 2, be the theory diagram of the structure speaker individual character sound bank of a kind of individual character voice of the utility model sound changing device.If need to build the individual character sound bank of certain speaker, by voice acquisition module (1), first gather the voice messaging of speaker, then build module (2) by the sound storehouse and voice messaging is carried out to the operations such as syllabification, the division of pure and impure sound and pitch period mark, obtain the basic voice messaging of this speaker, store individual character sound bank module (3) into.
As shown in Figure 3, the theory diagram that for a kind of individual character voice of the utility model sound changing device, the input voice is carried out to the change of voice of individual character voice.The voice messaging that at first by voice acquisition module (1) collection, need to carry out the change of voice of individual character voice, then pass through sound identification module (4) and identify the text message that it comprises.Text message is passed to voice synthetic module (5), then utilize the individual character sound bank of the speaker that needs the change of voice to be in individual character sound bank module (3) to carry out phonetic synthesis, finally synthetic voice transfer is exported to voice output module (6).
Claims (7)
1. an individual character voice sound changing device, is characterized in that this device comprises voice acquisition module (1), and the sound storehouse builds module (2), individual character sound bank module (3), sound identification module (4), voice synthetic module (5) and voice output module (6); Described voice acquisition module (1) connects respectively the sound storehouse and builds module (2) and sound identification module (4), and sound identification module (4) connects voice synthetic module (5) and voice output module (6) successively; The sound storehouse builds module (2) and connects individual character sound bank module (3), and individual character sound bank module (3) connects voice synthetic module (5) simultaneously.
2. a kind of individual character voice sound changing device according to claim 1, is characterized in that described voice acquisition module (1) is for the audio collection chip.
3. a kind of individual character voice sound changing device according to claim 1, is characterized in that described sound storehouse builds module (2) for pronounciation processing chip.
4. a kind of individual character voice sound changing device according to claim 1, is characterized in that described individual character sound bank module (3) is groups of memory chips.
5. a kind of individual character voice sound changing device according to claim 1, is characterized in that described sound identification module (4) is voice recognition chip.
6. a kind of individual character voice sound changing device according to claim 1, is characterized in that described voice synthetic module (5) is the PSOLA chipspeech.
7. a kind of individual character voice sound changing device according to claim 1, is characterized in that described voice output module (6) is for the audio frequency pio chip.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201320217640.9U CN203386472U (en) | 2013-04-26 | 2013-04-26 | Character voice changer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201320217640.9U CN203386472U (en) | 2013-04-26 | 2013-04-26 | Character voice changer |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN203386472U true CN203386472U (en) | 2014-01-08 |
Family
ID=49874931
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201320217640.9U Expired - Fee Related CN203386472U (en) | 2013-04-26 | 2013-04-26 | Character voice changer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN203386472U (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106328128A (en) * | 2016-08-16 | 2017-01-11 | 成都市和平科技有限责任公司 | Teaching system and method based on speech recognition technology |
| CN107481716A (en) * | 2017-07-31 | 2017-12-15 | 合肥上量机械科技有限公司 | A kind of computer speech aided input systems |
| CN109616131A (en) * | 2018-11-12 | 2019-04-12 | 南京南大电子智慧型服务机器人研究院有限公司 | A kind of number real-time voice is changed voice method |
| CN109859746A (en) * | 2019-01-22 | 2019-06-07 | 安徽声讯信息技术有限公司 | A kind of speech recognition corpus library generating method and system based on TTS |
| CN111383627A (en) * | 2018-12-28 | 2020-07-07 | 北京猎户星空科技有限公司 | Voice data processing method, device, equipment and medium |
-
2013
- 2013-04-26 CN CN201320217640.9U patent/CN203386472U/en not_active Expired - Fee Related
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106328128A (en) * | 2016-08-16 | 2017-01-11 | 成都市和平科技有限责任公司 | Teaching system and method based on speech recognition technology |
| CN107481716A (en) * | 2017-07-31 | 2017-12-15 | 合肥上量机械科技有限公司 | A kind of computer speech aided input systems |
| CN109616131A (en) * | 2018-11-12 | 2019-04-12 | 南京南大电子智慧型服务机器人研究院有限公司 | A kind of number real-time voice is changed voice method |
| CN109616131B (en) * | 2018-11-12 | 2023-07-07 | 南京南大电子智慧型服务机器人研究院有限公司 | Digital real-time voice sound changing method |
| CN111383627A (en) * | 2018-12-28 | 2020-07-07 | 北京猎户星空科技有限公司 | Voice data processing method, device, equipment and medium |
| CN111383627B (en) * | 2018-12-28 | 2024-03-22 | 北京猎户星空科技有限公司 | Voice data processing method, device, equipment and medium |
| CN109859746A (en) * | 2019-01-22 | 2019-06-07 | 安徽声讯信息技术有限公司 | A kind of speech recognition corpus library generating method and system based on TTS |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN203386472U (en) | Character voice changer | |
| CN101551998B (en) | A group of voice interaction devices and method of voice interaction with human | |
| US10776422B2 (en) | Dual sound source audio data processing method and apparatus | |
| US8909525B2 (en) | Interactive voice recognition electronic device and method | |
| CN108595443A (en) | Simultaneous interpreting method, device, intelligent vehicle mounted terminal and storage medium | |
| CN109754790B (en) | Speech recognition system and method based on hybrid acoustic model | |
| CN105244042B (en) | A kind of speech emotional interactive device and method based on finite-state automata | |
| CN104464727A (en) | Single-channel music singing separation method based on deep belief network | |
| CN105702250A (en) | Voice recognition method and device | |
| CN204496731U (en) | A kind of Voice command dictation device | |
| CN113436609B (en) | Voice conversion model, training method thereof, voice conversion method and system | |
| CN101471074A (en) | Method for converting voice into music of electronic device | |
| CN101694651A (en) | Speech translator | |
| CN109410918A (en) | For obtaining the method and device of information | |
| CN104123857A (en) | Device and method for achieving individualized touch reading | |
| CN207603881U (en) | A kind of intelligent sound wireless sound box | |
| CN203289645U (en) | Sound system capable of conversation based on wireless technology | |
| CN201532764U (en) | Vehicle-mounted sound-control wireless broadband network audio player | |
| CN202961892U (en) | Voice interaction toy | |
| CN112735382A (en) | Audio data processing method and device, electronic equipment and readable storage medium | |
| CN205017540U (en) | Wear -type K sings earphone | |
| CN203241996U (en) | Infant voice pocket-size translator | |
| CN107608976A (en) | A kind of unified speech play translating equipment with multiple functions | |
| CN114049875A (en) | TTS (text to speech) broadcasting method, device, equipment and storage medium | |
| CN204117387U (en) | A kind of equipment realizing personalized reading |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140108 Termination date: 20140426 |