CN102708858A - Voice bank realization voice recognition system and method based on organizing way - Google Patents
Voice bank realization voice recognition system and method based on organizing way Download PDFInfo
- Publication number
- CN102708858A CN102708858A CN2012102146028A CN201210214602A CN102708858A CN 102708858 A CN102708858 A CN 102708858A CN 2012102146028 A CN2012102146028 A CN 2012102146028A CN 201210214602 A CN201210214602 A CN 201210214602A CN 102708858 A CN102708858 A CN 102708858A
- Authority
- CN
- China
- Prior art keywords
- phonetic order
- voice
- speech recognition
- user
- terminal
- 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
Images
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The invention provides a voice bank realization voice recognition system based on an organizing way. The voice bank realization voice recognition system comprises a user terminal, a voice recognition terminal and a server terminal which are connected with each other through a network, wherein the user terminal can be used for setting a voice bank stored in the server terminal; the voice bank is grouped, and a part of needed command groups are called into a voice command stack for performing small-sized voice bank recognition judgment; and the voice recognition terminal is used for receiving a voice command transmitted by a user, converting the voice command into a voice command for searching for a corresponding command from the voice command stack, and operating equipment through the server terminal. The invention further provides a voice bank realization voice recognition method based on an organizing way. According the system and the method, the voice recognition system is optimized on the premise of not lowering the voice recognition rate of the equipment and on the basis of not lowering the recognition speed, the voice bank of handheld equipment is enlarged, the fault probability during recognition by a user according to voice is lowered, and the recognition capability during voice judgment is increased.
Description
Technical field
The present invention relates to a kind of sound bank and realize speech recognition system and method thereof based on organizational systems.
Background technology
Along with development of times and progress, change into literal or phonetic through voice; The technology that literal or phonetic change into voice is more and more ripe; The capacity of sound bank is also done bigger and bigger; Usually in the speech processes that is used for carrying out speech recognition and speaker identification; The quantity of information of the sound bank that relates to is all bigger, and the speech recognition engine identification that when carrying out speech recognition, makes the mistake easily like this makes it to carry out wrong operation.In the speech recognition engine in the prior art, have such problem: input speech signal when equipment carries out the speech recognition judgement, because the sound bank quantity of information is bigger, discrimination may descend when causing speech recognition engine to be judged.Therefore speech recognition engine is guaranteeing how to make speech recognition engine more excellent under the prerequisite that discrimination does not descend, to be a problem to be solved really when carrying out speech recognition.
Cloud Server; Be a kind ofly to serve based on WEB; The elasticity that can adjust cloud host configuration cloud is provided; Integrated Iaas (full name Infrastructure as a Service, promptly the infrastructure is promptly served) service of calculating, storage and Internet resources, possessed and use as required and the cloud host leasing service of instant ability of payment as required.On dirigibility, controllability, extendability and reusability of resources, all improve a lot.
Disclosing a kind of " domestic network system and control method thereof " publication number in the prior art is: CN102255780A; Open day be: the Chinese patent of 2011.11.23; Said domestic network system connects at least one electronics/electrical installation that each space of family is provided with through network, and its unique point is: speech recognition equipment, and it is provided with one within the family at least; And have speech identifying function and a distant control function; And be used to discern user's phonetic order, after the ID of itself and specified controlling object-electronics/electrical installation is mated, communicate by letter with transmitting control data through RF; Repeater; Be connected with said electronics/electrical installation in a predefined manner; And receive, restore from the control data of said speech recognition equipment through the RF communications, thereby ID is analyzed, and judge whether it is fill order to self; If just carry out the operation of the electronics/electrical installation that is connected, give said speech recognition equipment through the RF communications with the execution result of control operation.Said method comprising the steps of: when speech recognition equipment or repeater detect phonetic entry, just it is discerned and analyzes, thereby judge whether to include specified identification language; If do not include specified identification language, then the voice of oneself identification of deletion; If include specified identification language, then these voice be judged as phonetic order; Phonetic order is analyzed, extracted ID, and will to comprise control command be control data in interior speech conversion as the electronics/electrical installation of controlling object; Give the repeater that is connected on corresponding electronics/electrical installation with the RF communications with said control data; The ID that is comprised in the repeater analysis and Control data through RF communications reception control data, and judge to be the control command of self, if the control command of self then makes electronics/electrical installation carry out corresponding operating; And, then its result is sent the speech recognition equipment or the repeater of control data with transmission of RF signal and notice if according to control data executable operations through the RF communications reception.This invention has made up domestic network system, not only provides easy to use through the wireless home network of controlling based on speech recognition, but also has improved validity.But the problem that also can exist speech recognition engine when carrying out speech recognition, to make the mistake easily and discern in the wireless home network of the speech recognition of this invention.
Summary of the invention
One of technical matters that the present invention will solve is to provide a kind of sound bank based on organizational systems to realize speech recognition system, has reduced the error probability that produces when the user does identification according to voice.
One of problem of the present invention is achieved in that a kind of sound bank realization speech recognition system based on organizational systems, and said speech recognition system comprises through the interconnected at least one user terminal of network, at least one server end and a speech recognition terminal;
Said user terminal comprises terminal and mobile device terminal; Said mobile device terminal comprises mobile phone and panel computer.User terminal can be provided with the sound bank that exists in the server end, carries out remote update and revises sound bank, and can organize into groups setting to the voice in the sound bank; Be provided with a plurality of instruction groups in the said sound bank, be divided into one-level phonetic order and secondary phonetic order group in the said instruction group; The corresponding secondary phonetic order group of one-level phonetic order is provided with a plurality of secondary phonetic orders in each secondary phonetic order group; The one-level phonetic order is the group name of instruction group, and each secondary phonetic order is the operational order of relevant device in the secondary phonetic order group;
Said server end comprises a sound bank, has the user to edit in the sound bank said each instruction group is set, and every secondary phonetic order all has the corresponding equipment operational motion, and every phonetic order all is provided with a voice feedback information in the sound bank; After said voice feedback information is the phonetic order operational motion, the voice reminder information of carrying out;
Said speech recognition terminal is provided with a speech recognition engine and a voice command stack, and this speech recognition engine is used to collect the voice that the user sends, and voice is transferred to the phonetic order of literal or phonetic form or speech waveform; The voice command stack is provided with the instruction space, and this instruction space is used for depositing the instruction set that sends over from server end; Said instruction set is that phonetic order is inquired about all secondary phonetic order groups that obtain correspondence under the one-level phonetic order in the sound bank of server end; Select to want a certain secondary phonetic order of control operation equipment in all secondary phonetic orders that the user can obtain through inquiry, and bring in through server according to this secondary phonetic order relevant device is carried out the corresponding action operation.
Two of the technical matters that the present invention will solve is to provide a kind of sound bank based on organizational systems to realize audio recognition method.
Two of problem of the present invention is achieved in that a kind of sound bank realization audio recognition method based on organizational systems, comprises the steps:
There are the sound bank in the server end in step 10, user through a user terminal setting, instruct the group marshalling to be provided with to the voice in the sound bank, are divided into one-level phonetic order and secondary phonetic order group in the instruction group group; Said one-level phonetic order is used to indicate the group name of instruction group, and each secondary phonetic order is the operational order of relevant device in the said secondary phonetic order group; Said user terminal comprises terminal and mobile device terminal;
One-level phonetic order and secondary phonetic order group in step 20, each instruction group that will set are deposited in the sound bank, and the end that uploads onto the server upgrades sound bank;
Step 30, user send the voice of wanting operating equipment through a speech recognition terminal; Said speech recognition terminal is provided with a speech recognition engine and a voice command stack; This speech recognition engine receives the voice that the user sends, and voice is transferred to the phonetic order of literal or phonetic form or speech waveform; The user is when using a speech recognition terminal, and the voice that at first send will be the voice of one-level phonetic order;
Step 40, speech recognition terminal receive to transform to be transferred to behind the phonetic order of back searches for corresponding one-level phonetic order in the voice command stack, notify the user and make the speech recognition terminal get into holding state after searching corresponding one-level phonetic order; When search is less than the one-level phonetic order of correspondence in the voice command stack; The phonetic order transmission sent to and carries out sound bank search contrast in the server end after the speech recognition terminal will transform through network; As search the instruction group under the corresponding one-level phonetic order; Then, this instruction group is transferred to the said voice command stack in the speech recognition terminal through the instruction number of secondary phonetic order group in this instruction group of one-level phonetic order inquiry, and verbal announcement user and get into holding state;
Step 50, user are after obtaining one-level phonetic order notice; The user imports the secondary phonetic order; This secondary phonetic order will be the secondary phonetic order in the pairing secondary phonetic order of the one-level phonetic order group in the step 40, the user behind input secondary phonetic order, the secondary phonetic order that whether exists the user to import in the instruction group that the one-level phonetic order is corresponding in the determining step 40 in the voice command stack; As do not exist, then return step 40; As existing, send server end to according to the pairing operation of equipment action command of this secondary phonetic order after then in the voice command stack, searching this secondary phonetic order, server end carries out the corresponding action operation with corresponding equipment; Thereby completion speech recognition.
The present invention has following advantage: the present invention is under the prerequisite that the phonetic recognization rate that guarantees equipment does not descend; Speech recognition system is optimized; Reduced the error probability that produces when the user does identification according to voice; Operate through from sound bank, transferring out required a part of voice command, recognition capability strengthened when voice were differentiated.Through backing up sound bank in the Cloud Server, prevent that the wrong problem that causes user effort to be reset over head time from appearring in sound bank in user's the server end.Utilize and divide into groups the voice command of the equipment in the room is integrated, in the time will carrying out voice operating, need not consider the voice operating order of the equipment in other room, reduce user's operating mistake probability in current room; Also accelerated simultaneously the speech recognition operation of speech recognition engine to equipment.
Description of drawings
Fig. 1 is the structural framing figure of system of the present invention.
Fig. 2 is the schematic flow sheet of the inventive method.
Fig. 3 is provided with the schematic flow sheet of sound bank for user in the inventive method.
Fig. 4 is the schematic flow sheet of the overtime reflection in speech recognition terminal in the inventive method.
Embodiment
See also shown in Figure 1ly, a kind of sound bank based on organizational systems of the present invention is realized speech recognition system, and said speech recognition system comprises through the interconnected at least one user terminal of network, at least one server end and a speech recognition terminal;
Said user terminal comprises terminal and mobile device terminal; User terminal can be provided with the sound bank that exists in the server end, carries out remote update and revises sound bank, and can organize into groups setting to the voice in the sound bank; Be provided with a plurality of instruction groups in the said sound bank, be divided into one-level phonetic order and secondary phonetic order group in the said instruction group; The corresponding secondary phonetic order group of one-level phonetic order is provided with a plurality of secondary phonetic orders in each secondary phonetic order group; The one-level phonetic order is the group name of instruction group, and each secondary phonetic order is the operational order of relevant device in the secondary phonetic order group; Wherein, said mobile device terminal comprises mobile phone and panel computer;
Said server end is a server, has the function of data transmission, processing, storage, is used to receive and transmit the data message between said user terminal and the speech recognition terminal; Said server end comprises a sound bank, has the user to edit in the sound bank said each instruction group is set, and every secondary phonetic order all has the corresponding equipment operational motion, and every phonetic order all is provided with a voice feedback information in the sound bank; After said voice feedback information is the phonetic order operational motion, the voice reminder information of carrying out; (after having carried out any bar phonetic order operational motion, the voice reminder user: the voice reminder information of " you carried out so-and-so operation " and so on, can user oneself setting);
Said speech recognition terminal is provided with a speech recognition engine and a voice command stack, and this speech recognition engine is used to collect the voice that the user sends, and voice is transferred to the phonetic order of literal or phonetic form or speech waveform; The voice command stack is provided with the instruction space, and this instruction space is used for depositing the instruction set that sends over from server end; Said instruction set is that phonetic order is inquired about all secondary phonetic order groups and this one-level phonetic order that obtains correspondence under the one-level phonetic order in the sound bank of server end; Select to want a certain secondary phonetic order of control operation equipment in all secondary phonetic orders that the user can obtain through inquiry, and bring in through server according to this secondary phonetic order relevant device is carried out the corresponding action operation.Wherein, said speech recognition terminal is included as hand-held voice receiving equipment, mobile phone and the panel computer of capacity.
Wherein, the user can change or be provided with on user terminal by the password mode that the individual the likes secondary phonetic order that equipment is corresponding.The instruction space that is provided with in the voice command stack in the said speech recognition terminal; When the number of instructions of the instruction set that from server end, sends over exceeds the instruction space of said voice command stack, the instruction group at the bottom of the stack in the voice command stack is carried out deletion action, enough deposit until the instruction space.
To shown in Figure 4, a kind of sound bank based on organizational systems of the present invention is realized audio recognition method, comprises the steps: like Fig. 2
There are the sound bank in the server end in step 10, user through a user terminal setting, instruct the group marshalling to be provided with to the voice in the sound bank, are divided into one-level phonetic order and secondary phonetic order group in the instruction group group; Said one-level phonetic order is used to indicate the group name of instruction group, and each secondary phonetic order is the operational order of relevant device in the said secondary phonetic order group; (for example: TV, air-conditioning, refrigerator equipment are arranged in the room 001; Equipment such as TV, air-conditioning, refrigerator are also arranged in the room 002, then there is an one-level phonetic order in room 001, also there is an one-level phonetic order in room 002; TV in the room 001, air-conditioning, refrigerator equipment be respectively to should there being a plurality of secondary phonetic orders, each secondary phonetic order corresponding certain instruction action of relevant device, opening of air-conditioning for example, the pass of air-conditioning; TV in the room 002, air-conditioning, refrigerator equipment are also respectively to there being a plurality of secondary phonetic orders; Then the TV in the room 001, air-conditioning, refrigerator equipment are belonged under the one-level phonetic order in room 001 due secondary phonetic order respectively; TV in the room 002, air-conditioning, refrigerator equipment are belonged under the one-level phonetic order in room 002 due secondary phonetic order respectively; Then carry out division operation, each the secondary phonetic order formation secondary phonetic order group of correspondence with room 001 forms an instruction group with secondary phonetic order group and room 001 corresponding one-level phonetic order; Each secondary phonetic order of correspondence in room 002 is formed secondary phonetic order group, secondary phonetic order group and room 002 corresponding one-level phonetic order are formed an instruction group; ) said user terminal comprises terminal and mobile device terminal; Said mobile device terminal comprises mobile phone and panel computer; Wherein, the user can change or be provided with on user terminal by the password mode that the individual the likes secondary phonetic order that equipment is corresponding;
One-level phonetic order and secondary phonetic order group in step 20, each instruction group that will set are deposited in the sound bank, and the end that uploads onto the server upgrades sound bank;
Step 30, user send the voice of wanting operating equipment through a speech recognition terminal; Said speech recognition terminal is provided with a speech recognition engine and a voice command stack; This speech recognition engine receives the voice that the user sends, and voice is transferred to the phonetic order of literal or phonetic form or speech waveform; Said speech recognition terminal is included as self-control hand-held voice receiving equipment, mobile phone or the panel computer of capacity; The user is when using a speech recognition terminal, and the voice that at first send will be the voice of one-level phonetic order;
Step 40, speech recognition terminal receive to transform to be transferred to behind the phonetic order of back searches for corresponding one-level phonetic order in the voice command stack, notify the user and make the speech recognition terminal get into holding state after searching corresponding one-level phonetic order; When search is less than the one-level phonetic order of correspondence in the voice command stack; The phonetic order transmission sent to and carries out sound bank search contrast in the server end after the speech recognition terminal will transform through network; As search the instruction group under the corresponding one-level phonetic order; Then, this instruction group is transferred to the said voice command stack in the speech recognition terminal through the instruction number of secondary phonetic order group in this instruction group of one-level phonetic order inquiry, and verbal announcement user and get into holding state;
Step 50, user are after obtaining one-level phonetic order notice; The user imports the secondary phonetic order; This secondary phonetic order will be the secondary phonetic order in the pairing secondary phonetic order of the one-level phonetic order group in the step 40, the user behind input secondary phonetic order, the secondary phonetic order that whether exists the user to import in the instruction group that the one-level phonetic order is corresponding in the determining step 40 in the voice command stack; As do not exist, then return step 40; As existing, send server end to according to the pairing operation of equipment action command of this secondary phonetic order after then in the voice command stack, searching this secondary phonetic order, server end carries out the corresponding action operation with corresponding equipment; Thereby completion speech recognition.
As shown in Figure 4, in step 60, the setting-up time after speech recognition is accomplished, the speech recognition terminal does not have the new phonetic order of reception, and then original state is got back at the speech recognition terminal.(promptly can't select, need re-enter one-level phonetic order selection instruction group) according to the secondary phonetic order of preceding once input
Wherein, the instruction space that is provided with in the voice command stack in the said speech recognition terminal; [white rabbit 1] space instructions stored also is a multilevel hierarchy; When the number of instructions of the instruction group that from server end, sends over exceeds the instruction space of said voice command stack; One-level phonetic order at the bottom of the stack in the voice inquirement command stack; Obtain the affiliated instruction group of this one-level phonetic order; With deletion action at the bottom of the stack of its instruction group from the voice command stack, enough deposit until the instruction space.
When in the voice command stack and in the sound bank of server end, all not searching the one-level phonetic order that the user sends, carry out voice feedback notice user inquiring less than this phonetic order, please re-enter.
In a word; The present invention is under the prerequisite that the phonetic recognization rate that guarantees equipment does not descend and on the basis that do not reduce of recognition speed; Speech recognition system is optimized; Reduced the error probability that produces when the user does identification according to voice, carried out small-sized sound bank identification decision operation to the speech recognition terminal through from sound bank, transferring out required a part of voice command, recognition capability strengthened when voice were differentiated.Utilize packet mode that sound bank is organized into groups, organize and carry out the identification of small-sized sound bank in the voice command stack and judge from sound bank, transferring the required instruction of a part, reduce user's operating mistake probability; Simultaneously also accelerated the speech recognition operation of speech recognition engine, recognition speed is accelerated equipment.
The above is merely preferred embodiment of the present invention, and all equalizations of doing according to claim of the present invention change and modify, and all should belong to covering scope of the present invention.
The words need not explain in claims that this sentence is a declarative statement, and has the qualification effect, therefore in instructions, explains to get final product
Claims (10)
1. the sound bank based on organizational systems is realized speech recognition system, and it is characterized in that: said speech recognition system comprises through the interconnected at least one user terminal of network, at least one server end and a speech recognition terminal;
Said user terminal comprises terminal and mobile device terminal; Said mobile device terminal comprises mobile phone and panel computer; User terminal can be provided with the sound bank that exists in the server end, carries out remote update and revises sound bank, and can organize into groups setting to the voice in the sound bank; Be provided with a plurality of instruction groups in the said sound bank, be divided into one-level phonetic order and secondary phonetic order group in the said instruction group; The corresponding secondary phonetic order group of one-level phonetic order is provided with a plurality of secondary phonetic orders in each secondary phonetic order group; The one-level phonetic order is the group name of instruction group, and each secondary phonetic order is the operational order of relevant device in the secondary phonetic order group;
Said server end comprises a sound bank, has the user to edit in the sound bank said each instruction group is set, and every secondary phonetic order all has the corresponding equipment operational motion, and every phonetic order all is provided with a voice feedback information in the sound bank; After said voice feedback information is the phonetic order operational motion, the voice reminder information of carrying out;
Said speech recognition terminal is provided with a speech recognition engine and a voice command stack, and this speech recognition engine is used to collect the voice that the user sends, and voice is transferred to the phonetic order of literal or phonetic form or speech waveform; The voice command stack is provided with the instruction space, and this instruction space is used for depositing the instruction set that sends over from server end; Said instruction set is that phonetic order is inquired about all secondary phonetic order groups and this one-level phonetic order that obtains correspondence under the one-level phonetic order in the sound bank of server end; Select to want a certain secondary phonetic order of control operation equipment in all secondary phonetic orders that the user can obtain through inquiry, and bring in through server according to this secondary phonetic order relevant device is carried out the corresponding action operation.
2. the sound bank based on organizational systems according to claim 1 is realized speech recognition system, and it is characterized in that: said speech recognition terminal is included as hand-held voice receiving equipment, mobile phone and the panel computer of capacity.
3. the sound bank based on organizational systems according to claim 1 is realized speech recognition system, it is characterized in that: the user can change or be provided with on user terminal by the password mode that the individual the likes secondary phonetic order that equipment is corresponding.
4. the sound bank based on organizational systems according to claim 1 is realized speech recognition system, it is characterized in that: the instruction space that is provided with in the voice command stack in the said speech recognition terminal; When the number of instructions of the instruction set that from server end, sends over exceeds the instruction space of said voice command stack, the instruction group at the bottom of the stack in the voice command stack is carried out deletion action, enough deposit until the instruction space.
5. the sound bank based on organizational systems is realized audio recognition method, it is characterized in that: comprise the steps:
There are the sound bank in the server end in step 10, user through a user terminal setting, instruct the group marshalling to be provided with to the voice in the sound bank, are divided into one-level phonetic order and secondary phonetic order group in the instruction group group; Said one-level phonetic order is used to indicate the group name of instruction group, and each secondary phonetic order is the operational order of relevant device in the said secondary phonetic order group; Said user terminal comprises terminal and mobile device terminal;
One-level phonetic order and secondary phonetic order group in step 20, each instruction group that will set are deposited in the sound bank, and the end that uploads onto the server upgrades sound bank;
Step 30, user send the voice of wanting operating equipment through a speech recognition terminal; Said speech recognition terminal is provided with a speech recognition engine and a voice command stack; This speech recognition engine receives the voice that the user sends, and voice is transferred to the phonetic order of literal or phonetic form or speech waveform; The user is when using a speech recognition terminal, and the voice that at first send will be the voice of one-level phonetic order;
Step 40, speech recognition terminal receive to transform to be transferred to behind the phonetic order of back searches for corresponding one-level phonetic order in the voice command stack, notify the user and make the speech recognition terminal get into holding state after searching corresponding one-level phonetic order; When search is less than the one-level phonetic order of correspondence in the voice command stack; The phonetic order transmission sent to and carries out sound bank search contrast in the server end after the speech recognition terminal will transform through network; As search the instruction group under the corresponding one-level phonetic order; Then, this instruction group is transferred to the said voice command stack in the speech recognition terminal through the instruction number of secondary phonetic order group in this instruction group of one-level phonetic order inquiry, and verbal announcement user and get into holding state;
Step 50, user are after obtaining one-level phonetic order notice; The user imports the secondary phonetic order; This secondary phonetic order will be the secondary phonetic order in the pairing secondary phonetic order of the one-level phonetic order group in the step 40, the user behind input secondary phonetic order, the secondary phonetic order that whether exists the user to import in the instruction group that the one-level phonetic order is corresponding in the determining step 40 in the voice command stack; As do not exist, then return step 40; As existing, send server end to according to the pairing operation of equipment action command of this secondary phonetic order after then in the voice command stack, searching this secondary phonetic order, server end carries out the corresponding action operation with corresponding equipment; Thereby completion speech recognition.
6. the sound bank based on organizational systems according to claim 5 is realized audio recognition method, and it is characterized in that: said mobile device terminal comprises mobile phone and panel computer.
7. the sound bank based on organizational systems according to claim 5 is realized audio recognition method, it is characterized in that: specifically also comprise in the said step 10: the user can change or be provided with on user terminal by the password mode that the individual the likes password that equipment is corresponding.
8. the sound bank based on organizational systems according to claim 5 is realized audio recognition method, it is characterized in that: specifically also comprise in the said step 40: the instruction space that is provided with in the voice command stack in the said speech recognition terminal; When the number of instructions of the instruction group that from server end, sends over exceeds the instruction space of said voice command stack; One-level phonetic order at the bottom of the stack in the voice inquirement command stack; Obtain the affiliated instruction group of this one-level phonetic order; With deletion action at the bottom of the stack of its instruction group from the voice command stack, enough deposit until the instruction space.
9. the sound bank based on organizational systems according to claim 5 is realized audio recognition method; It is characterized in that: in the voice command stack with in the sound bank of server end, all do not search the words of the one-level phonetic order that the user sends; Carry out voice feedback notice user inquiring less than this phonetic order, please re-enter.
10. the sound bank based on organizational systems according to claim 5 is realized audio recognition method, it is characterized in that: also further comprise after the said step 50:
In step 60, the setting-up time after speech recognition is accomplished, the speech recognition terminal does not have the new phonetic order of reception, and then original state is got back at the speech recognition terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012102146028A CN102708858A (en) | 2012-06-27 | 2012-06-27 | Voice bank realization voice recognition system and method based on organizing way |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012102146028A CN102708858A (en) | 2012-06-27 | 2012-06-27 | Voice bank realization voice recognition system and method based on organizing way |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102708858A true CN102708858A (en) | 2012-10-03 |
Family
ID=46901560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012102146028A Pending CN102708858A (en) | 2012-06-27 | 2012-06-27 | Voice bank realization voice recognition system and method based on organizing way |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102708858A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104123941A (en) * | 2014-07-17 | 2014-10-29 | 常州蓝城信息科技有限公司 | Method for using voice recognition to control device |
| CN104217720A (en) * | 2013-05-29 | 2014-12-17 | 腾讯科技（深圳）有限公司 | Mail list speech recognition method, system and device based on short connections |
| CN106251863A (en) * | 2016-07-26 | 2016-12-21 | 傲爱软件科技（上海）有限公司 | A kind of instruction type speech control system based on smart machine and control method |
| CN106601250A (en) * | 2015-11-10 | 2017-04-26 | 刘芨可 | Speech control method and device and equipment |
| CN106679915A (en) * | 2016-12-16 | 2017-05-17 | 南京航空航天大学 | Vibration test experimental method and system based on intelligent voice control |
| WO2017143692A1 (en) * | 2016-02-26 | 2017-08-31 | 深圳Tcl数字技术有限公司 | Smart television and voice control method therefor |
| WO2017219519A1 (en) * | 2016-06-24 | 2017-12-28 | 中兴通讯股份有限公司 | Method, apparatus, and system for controlling device |
| CN110956964A (en) * | 2019-11-27 | 2020-04-03 | 捷开通讯(深圳)有限公司 | Method, apparatus, storage medium and terminal for providing voice service |
| CN113113019A (en) * | 2021-03-27 | 2021-07-13 | 上海红阵信息科技有限公司 | Voice library generating system and method |
| TWI739067B (en) * | 2019-02-13 | 2021-09-11 | 華南商業銀行股份有限公司 | Cross-channel artificial intelligence dialogue platform and operation method thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001001389A2 (en) * | 1999-06-24 | 2001-01-04 | Siemens Aktiengesellschaft | Voice recognition method and device |
| CN1361516A (en) * | 2000-12-28 | 2002-07-31 | 广东科龙电器股份有限公司 | Comprehensive household server |
| CN1609951A (en) * | 2003-10-18 | 2005-04-27 | 鸿富锦精密工业（深圳）有限公司 | Long-distance speech control system and method |
| CN1797543A (en) * | 2004-12-23 | 2006-07-05 | 上海电气自动化设计研究所有限公司 | Device and method of industrial robot possessing capability of recognizing voice command |
| CN102332265A (en) * | 2011-06-20 | 2012-01-25 | 浙江吉利汽车研究院有限公司 | Method for improving voice recognition rate of automobile voice control system |
-
2012
- 2012-06-27 CN CN2012102146028A patent/CN102708858A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001001389A2 (en) * | 1999-06-24 | 2001-01-04 | Siemens Aktiengesellschaft | Voice recognition method and device |
| CN1361516A (en) * | 2000-12-28 | 2002-07-31 | 广东科龙电器股份有限公司 | Comprehensive household server |
| CN1609951A (en) * | 2003-10-18 | 2005-04-27 | 鸿富锦精密工业（深圳）有限公司 | Long-distance speech control system and method |
| CN1797543A (en) * | 2004-12-23 | 2006-07-05 | 上海电气自动化设计研究所有限公司 | Device and method of industrial robot possessing capability of recognizing voice command |
| CN102332265A (en) * | 2011-06-20 | 2012-01-25 | 浙江吉利汽车研究院有限公司 | Method for improving voice recognition rate of automobile voice control system |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104217720A (en) * | 2013-05-29 | 2014-12-17 | 腾讯科技（深圳）有限公司 | Mail list speech recognition method, system and device based on short connections |
| CN104217720B (en) * | 2013-05-29 | 2019-03-01 | 腾讯科技（深圳）有限公司 | A kind of mthods, systems and devices for realizing address list speech recognition based on short connection |
| CN104123941A (en) * | 2014-07-17 | 2014-10-29 | 常州蓝城信息科技有限公司 | Method for using voice recognition to control device |
| CN106601250A (en) * | 2015-11-10 | 2017-04-26 | 刘芨可 | Speech control method and device and equipment |
| WO2017143692A1 (en) * | 2016-02-26 | 2017-08-31 | 深圳Tcl数字技术有限公司 | Smart television and voice control method therefor |
| WO2017219519A1 (en) * | 2016-06-24 | 2017-12-28 | 中兴通讯股份有限公司 | Method, apparatus, and system for controlling device |
| CN106251863A (en) * | 2016-07-26 | 2016-12-21 | 傲爱软件科技（上海）有限公司 | A kind of instruction type speech control system based on smart machine and control method |
| CN106679915A (en) * | 2016-12-16 | 2017-05-17 | 南京航空航天大学 | Vibration test experimental method and system based on intelligent voice control |
| CN106679915B (en) * | 2016-12-16 | 2019-04-19 | 南京航空航天大学 | A kind of vibration experiments method and system based on intelligent sound control |
| TWI739067B (en) * | 2019-02-13 | 2021-09-11 | 華南商業銀行股份有限公司 | Cross-channel artificial intelligence dialogue platform and operation method thereof |
| CN110956964A (en) * | 2019-11-27 | 2020-04-03 | 捷开通讯(深圳)有限公司 | Method, apparatus, storage medium and terminal for providing voice service |
| CN113113019A (en) * | 2021-03-27 | 2021-07-13 | 上海红阵信息科技有限公司 | Voice library generating system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102708858A (en) | Voice bank realization voice recognition system and method based on organizing way | |
| CN102708865A (en) | Method, device and system for voice recognition | |
| CN106448658B (en) | The sound control method and intelligent domestic gateway of smart home device | |
| CN103915095B (en) | The method of speech recognition, interactive device, server and system | |
| EP2495936A1 (en) | Server for grouping devices based on sounds collected and method therefor | |
| CN102830687B (en) | Intelligent home control system and method | |
| CN102568178B (en) | Remote control system and remote control method | |
| CN104536647B (en) | The location regulation method and device of application icon | |
| CN107566226A (en) | A kind of methods, devices and systems for controlling smart home | |
| CN104715752A (en) | Voice recognition method, voice recognition device and voice recognition system | |
| US20160132029A1 (en) | Method for configuring and controlling smart home products | |
| CN102740014A (en) | Voice controlled television, television system and method for controlling television through voice | |
| CN104010267A (en) | Method and system for supporting a translation-based communication service and terminal supporting the service | |
| US8407158B2 (en) | System and method for providing interactive troubleshooting | |
| CN106251873A (en) | Sound control method and speech control system | |
| CN109600636A (en) | Interactive server, display equipment and its control method | |
| CN104681025B (en) | Utilize the order execution system and its method of work of speech recognition | |
| WO2014176894A1 (en) | Voice processing method and terminal | |
| CN105652674A (en) | Wireless voice unvarnished transmission device and control terminal | |
| CN109117235A (en) | A kind of business data processing method, device and relevant device | |
| US10204098B2 (en) | Method and system to communicate between devices through natural language using instant messaging applications and interoperable public identifiers | |
| CN110910541A (en) | Access control method, system, network device and computer readable storage medium | |
| CN107483993A (en) | Pronunciation inputting method, TV and the computer-readable recording medium of TV | |
| CN103139291B (en) | A kind of location application server obtains the method for terminal gps data | |
| CN102508543A (en) | Man-machine interactive system for digital terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20121003 |