CN202584717U - Speech recognition device and speed control system - Google Patents

Speech recognition device and speed control system Download PDF

Info

Publication number
CN202584717U
CN202584717U CN 201220120812 CN201220120812U CN202584717U CN 202584717 U CN202584717 U CN 202584717U CN 201220120812 CN201220120812 CN 201220120812 CN 201220120812 U CN201220120812 U CN 201220120812U CN 202584717 U CN202584717 U CN 202584717U
Authority
CN
China
Prior art keywords
module
matching
identification
voice
action
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
Application number
CN 201220120812
Other languages
Chinese (zh)
Inventor
柏光宾
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
BEIJING TENGRUIWANLI TECHNOLOGY Co Ltd
Original Assignee
BEIJING TENGRUIWANLI TECHNOLOGY Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by BEIJING TENGRUIWANLI TECHNOLOGY Co Ltd filed Critical BEIJING TENGRUIWANLI TECHNOLOGY Co Ltd
Priority to CN 201220120812 priority Critical patent/CN202584717U/en
Application granted granted Critical
Publication of CN202584717U publication Critical patent/CN202584717U/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Images

Landscapes

  • Telephonic Communication Services (AREA)

Abstract

The utility model discloses a speech recognition device and a speech control system. The device comprises a speech receiving module, a first recognition module, a switch module and a second recognition module, wherein the first recognition module is used for recognizing and matching received speech information, generating and sending a starting control command to the switch module to communicate the switch module; the switch module is used for communicating the speech receiving module and the second recognition module according to the starting control command; and the second recognition module is used for recognizing and matching through the speech information received by the switch module, and generating and sending an action command to execute an action set in advance when an action speech information is matched. The speech recognition device and the speech control system disclosed by the utility model control the switch module to communicate the second recognition module and the speech receiving module by recognizing the starting speech information through setting the first recognition module and carry out complex speech recognition through the second speech recognition module; so that the device and system are more in accordance with natural use scenes, improve use convenience for users and reduce the possibility of speech misoperation.

Description

Speech recognition equipment and speech control system
Technical field
The utility model relates to speech recognition technology, relates in particular to a kind of speech recognition equipment and speech control system.
Background technology
Speech recognition technology is meant that equipment such as computing machine or machinery can understand the technology of people's voice automatically, utilizes speech recognition technology can make equipment such as computing machine carry out corresponding action according to people's voice.
Existing speech recognition equipment is provided with start button usually, and after triggering start button, speech recognition equipment gets into the speech recognition state, records and a series of actions such as identification, finally accomplishes speech recognition.The above-mentioned mode that is provided with start button, the user still will seek start button when busy sometimes, could start speech recognition equipment work, operates more loaded down with trivial details.
Art technology worker hopes to find a kind ofly can not need start button; Be in the method for speech recognition whenever and wherever possible; But there is following defective in the speech recognition meeting of carrying out that continues: 1) because voice to be identified possibly comprise a plurality of entries; These entries inevitably can be mentioned, thereby are easy to generate maloperation; 2) speech recognition that continues receives factor affecting such as environment to be difficult to adopt the cloud voice to discern.
The utility model content
The utility model provides a kind of speech recognition equipment and speech control system, to solve defective of the prior art, improves the convenience that the user uses, and reduces the misuse rate of speech recognition.
The utility model provides a kind of speech recognition equipment, wherein, comprising:
The voice receiver module that is used for receiving speech information;
Be used for the voice messaging that receives is carried out identification and matching, when matching opening voice information, produce and send first identification module that the said switch module of control is communicated with the unlatching steering order of the said voice receiver module and second identification module to switch module;
Be used for being communicated with according to said unlatching steering order the switch module of the said voice receiver module and second identification module, said switch module links to each other with second identification module with said voice receiver module, said first identification module respectively;
Be used for the voice messaging that receives through said switch module is carried out identification and matching, when matching the action voice messaging, produce and send second identification module of the action command of carrying out predetermined action.
Aforesaid speech recognition equipment, wherein, preferably, said first identification module comprises:
Be used to store first storage unit of entry;
Be used for the voice messaging that receives is discerned, and first matching unit that the entry in the voice messaging that identifies and first storage unit is mated;
Be used for when first matching unit matches opening voice information, produce and send the unlatching control module of the unlatching steering order that the said switch module of control is communicated with to said switch module.
Aforesaid speech recognition equipment, wherein, preferably, said second identification module comprises:
Be used to store second storage unit of at least one entry;
Be used for the voice messaging that receives through said switch module is discerned, and second matching unit that the entry in the voice messaging that identifies and second storage unit is mated;
Be used for when second matching unit matches the action voice messaging, producing and send first instruction execution unit of the action command of carrying out predetermined action.
Aforesaid speech recognition equipment, wherein, preferably, said second identification module comprises:
Be used for and be sent to the network platform through the voice messaging that said switch module receives, carrying out identification and matching, and receive the 3rd matching unit of the matching result that returns;
When the matching result that is used for receiving when said the 3rd matching unit moves voice messaging for matching, produce and send second instruction execution unit of the action command of carrying out predetermined action.
Aforesaid speech recognition equipment wherein, preferably, also comprises:
Be used for the voice messaging that receives is carried out identification and matching,, produce and send the 3rd identification module that the said switch module of control breaks off the closing control instruction of the said voice receiver module and second identification module to switch module when matching when closing voice messaging.
Aforesaid speech recognition equipment wherein, preferably, also comprises:
The action recognition module when being used to monitor said action command and being finished, produces also and sends the closing control instruction that the said switch module of control breaks off to switch module.
The utility model also provides a kind of speech control system, comprises action module, and among its spy, said system also comprises the speech recognition equipment that the utility model provides; Said action module links to each other with said second identification module, is used for carrying out corresponding actions according to the said action command that receives.
Speech recognition equipment that the utility model provides and speech control system are discerned the opening voice information of setting and are come the CS module through first identification module is set; Thereby be communicated with second identification module and the voice receiver module carries out work; Carry out complicated speech recognition through second identification module, compared with prior art, more meet nature and use scene; Improve the convenience that the user uses, reduced the possibility of voice maloperations.
Description of drawings
The speech recognition equipment structural representation that Fig. 1 provides for the utility model embodiment one.
The structural representation of first identification module in the speech recognition equipment that Fig. 2 provides for the utility model embodiment one.
The structural representation of second identification module in the speech recognition equipment that Fig. 3 provides for the utility model embodiment one.
The structural representation of second identification module in the speech recognition equipment that Fig. 4 provides for the utility model embodiment two.
The speech control system structural representation that Fig. 5 provides for the utility model embodiment three.
Embodiment
Embodiment one
The speech recognition equipment structural representation that Fig. 1 provides for the utility model embodiment one; The utility model embodiment one provides a kind of speech recognition equipment; Be applicable to computing machine, machinery or communication facilities; For example mobile phone, navigating instrument etc., this speech recognition equipment comprise voice receiver module 1, first identification module 2, switch module 3 and second identification module 4, and wherein voice receiver module 1 is used for receiving speech information; First identification module 2 is used for the voice messaging that receives is carried out identification and matching, when matching opening voice information, and generation and the unlatching steering order that is communicated with to the said switch module 3 of switch module 3 transmission controls; Switch module 3 links to each other with voice receiver module 1, first identification module 2 and second identification module 4 respectively, is used for being communicated with the voice receiver module 1 and second identification module 4 according to opening steering order; Second identification module 4 is used for the voice messaging that receives through switch module 3 is carried out identification and matching, when matching the action voice messaging, produces and send the action command of carrying out predetermined action.
The course of work of present embodiment is following: voice receiver module 1 continues receiving speech information; 2 pairs of voice messagings that receive of first identification module carry out identification and matching; When matching as the fixed phrase of opening voice information or vocabulary; This first identification module 2 can produce a steering order, the instruction whether this steering order ability CS module 3 makes voice receiver module 1 be connected with second identification module 4; When second identification module 4 with after voice receiver module 1 is communicated with; Second identification module 4 promptly can receive the voice messaging that voice receiver module 1 transmits and carry out identification and matching; When matching the action voice messaging that is provided with in advance; Can produce and send preset action command, this instruction can be controlled corresponding module and carry out predetermined action, thereby realizes the specific tasks of concrete equipment.So-called switch module 3 is with the connection of the voice receiver module 1 and second identification module 4; Specifically various ways can be arranged; For example directly be electrically connected through hardware switch; Perhaps control modes such as the voice messaging that whether will transfer to second identification module 4 abandons through software and hardware combining, present embodiment does not limit this, as long as make second identification module 4 can begin voice messaging is handled through the connection of switch module 4.
Compared with prior art; The speech recognition equipment that present embodiment provides comes the CS module through first identification module is set; Be communicated with thereby when recognizing the opening voice information of setting, make between voice receiver module and second recognition device, second recognition device carries out identification and matching to the voice messaging that receives then, according to the action voice messaging that matches; Send command adapted thereto, carry out predetermined action.Compare with the mode opening voice identification that utilizes start button in the prior art; More convenient operation adopts two identification modules simultaneously, utilizes first identification module to control second identification module and whether accepts voice messaging; Thereby the execution corresponding actions can reduce the possibility of voice maloperation.Both having need not start button can discern by opening voice, can not carry out uncontrolled continuous identification to the voice messaging that continues to receive again.
The structural representation of first identification module in the speech recognition equipment that Fig. 2 provides for the utility model embodiment; In the present embodiment; First identification module 2 comprises first storage unit 21, first matching unit 22 and opens control module 23 that wherein, first storage unit 21 is used to store entry; First matching unit 22 is used for the voice messaging that receives is discerned, and the entry in the voice messaging that identifies and first storage unit 21 is mated; Open control module 23 and be used for when first matching unit 22 matches opening voice information, generation and the unlatching steering order that is communicated with to switch module transmission CS module.
It will be understood by those skilled in the art that identifying was divided into two stages when the speech recognition equipment of using the utility model embodiment and providing carried out speech recognition:
Phase one, voice receiver module 1 continues receiving speech information, and first identification module 2 carries out identification and matching based on the entry in first storage unit 21; Because what said process adopted is local identification mode, the entry negligible amounts that relates to, response speed is fast; When matching the opening voice information of setting, for example pre-set fixedly vocabulary, fixing statement etc., identification and matching success; This moment, first identification module 2 was to switch module 3 sending controling instructions; This steering order is controlled second identification module 4 and is communicated with voice receiver module 1, thereby identifying gets into subordinate phase; The first above-mentioned identification module 2 is just as a lock, and the opening voice information of setting similarly is key, and key is few more, and security is just good more, can reduce the voice maloperation accordingly;
Subordinate phase; After second identification module 4 matees successfully in the phase one; Because switch module 3 is communicated with the voice receiver module 1 and second identification module 4; Make second identification module can get access to the voice messaging that voice receiver module place receives, thereby second identification module can begin the identification and matching work of voice messaging, when identification and matching produces and send action command behind the action voice messaging of setting; For example can action command be sent to the action module in the equipment, to carry out deliberate action.In subordinate phase, second identification module 4 can be discerned the voice of multiple complicacy, also can use multiple identifying schemes.
The structure of second identification module 4 can have multiple, realizes the different voice identifying schemes, the structural representation of second identification module in the speech recognition equipment that Fig. 3 provides for the utility model embodiment one; Particularly; Please with reference to Fig. 3, a kind of embodiment is, second identification module 4 comprises second storage unit 41, second matching unit 42 and first instruction execution unit 43; Wherein, second storage unit 41 is used to store at least one entry; Second matching unit 42 is used for the voice messaging that receives through switch module 3 is discerned, and the entry in the voice messaging that identifies and second storage unit 41 is mated; First instruction execution unit 43 is used for when second matching unit 42 matches the action voice messaging, producing and send the action command of carrying out predetermined action.At this moment, the action of the identification and matching of second identification module 4 also is the process of local identification, and similar with the identification and matching action of first identification module 2, its response speed is very fast.
The speech recognition equipment that the utility model embodiment one provides is discerned the opening voice information of setting and is come the CS module through first identification module is set; Thereby be communicated with second identification module and the voice receiver module carries out work; Carry out complicated speech recognition through second identification module, compare more convenient operation with the mode opening voice identification that utilizes start button in the prior art; Adopt two identification modules simultaneously; Utilize first identification module to control second identification module and whether accept voice messaging, thereby carry out corresponding actions, can reduce the possibility of voice maloperation.
Embodiment two
The structural representation of second identification module in the speech recognition equipment that Fig. 4 provides for the utility model embodiment two; Please with reference to Fig. 4, with the difference of embodiment one be: the another kind of embodiment of second identification module 4 is that second identification module 4 comprises the 3rd matching unit 44 and second instruction execution unit 45; Wherein, The 3rd matching unit 44 is used for the voice messaging that receives through switch module 3 is sent to the network platform 6, carrying out identification and matching, and receives the matching result that returns; When the matching result that second instruction execution unit 45 is used for receiving when the 3rd matching unit 44 moves voice messaging for matching, produce and also send the action command of carrying out predetermined action.At this moment; The 3rd matching unit 44 is that the entry that is used for platform 6 Network Based receives matching result; The utilization of the network platform 6 makes speech recognition equipment can use the cloud voice to discern, and the entry of the network platform 6 is more, makes the application of speech recognition equipment extensive more flexibly.
Preferably, above-mentioned speech recognition equipment also comprises the 3rd identification module, is used for the voice messaging that receives is carried out identification and matching, when matching when closing voice messaging, produces and sends the closing control instruction that the CS module is broken off to switch module.The user can preset fixing statement or vocabulary is used as turn-offing voice messaging; When the speech recognition equipment identification and matching to these fixedly when statement or vocabulary; Just can the CS module break off the voice receiver module and second identification module; Make second identification module no longer receive voice messaging, thereby finish identification maneuver.
Speech recognition equipment finishes identification maneuver also can be realized through the action recognition module is set; When this action recognition module is used to monitor action command and is finished, produce and send the closing control instruction that the CS module is broken off the voice receiver module and second identification module to switch module.For example; The action recognition module can realize its observation process through the mode that sensor is set; On the concrete equipment of carrying out corresponding actions or concrete parts, sensor is set, after action was finished, the action recognition module received the completed information of action through sensor; Judge action command and be finished, thereby produce and send closing control to switch module and instruct.
Speech recognition equipment that the utility model embodiment two provides and speech control system are discerned the opening voice information of setting and are come the CS module through first identification module is set; Switch module is communicated with second identification module and the voice receiver module carries out work; Carry out complicated speech recognition through second identification module, compared with prior art, omitted and released the button; But utilize first identification module as " key " that start the second module receiving speech information; Compared with prior art, more meet nature and use scene, improved the convenience that the user uses; Switch module is set simultaneously can makes the identification and matching realization of second identification module controlled, reduced the possibility of voice maloperations.
The speech control system structural representation that Fig. 5 provides for the utility model embodiment three; As shown in Figure 5, the utility model embodiment three provides a kind of speech control system, comprises action module 5; Wherein, This system also comprises the speech recognition equipment that the utility model any embodiment provides, and this action module 5 links to each other with second identification module 4, is used for carrying out corresponding actions according to the action command that receives.
What should explain at last is: above embodiment is only in order to the technical scheme of explanation the utility model, but not to its restriction; Although the utility model has been carried out detailed explanation with reference to previous embodiment; Those of ordinary skill in the art is to be understood that: it still can be made amendment to the technical scheme that aforementioned each embodiment put down in writing, and perhaps part technical characterictic wherein is equal to replacement; And these are revised or replacement, do not make the scope of each embodiment technical scheme of essence disengaging the utility model of relevant art scheme.

Claims (7)

1. a speech recognition equipment is characterized in that, comprising:
The voice receiver module that is used for receiving speech information;
Be used for the voice messaging that receives is carried out identification and matching, when matching opening voice information, produce and send first identification module that the said switch module of control is communicated with the unlatching steering order of the said voice receiver module and second identification module to switch module;
Be used for being communicated with according to said unlatching steering order the switch module of the said voice receiver module and second identification module, said switch module links to each other with second identification module with said voice receiver module, said first identification module respectively;
Be used for the voice messaging that receives through said switch module is carried out identification and matching, when matching the action voice messaging, produce and send second identification module of the action command of carrying out predetermined action.
2. speech recognition equipment according to claim 1 is characterized in that, said first identification module comprises:
Be used to store first storage unit of entry;
Be used for the voice messaging that receives is discerned, and first matching unit that the entry in the voice messaging that identifies and first storage unit is mated;
Be used for when first matching unit matches opening voice information, produce and send the unlatching control module of the unlatching steering order that the said switch module of control is communicated with to said switch module.
3. speech recognition equipment according to claim 1 is characterized in that, said second identification module comprises:
Be used to store second storage unit of at least one entry;
Be used for the voice messaging that receives through said switch module is discerned, and second matching unit that the entry in the voice messaging that identifies and second storage unit is mated;
Be used for when second matching unit matches the action voice messaging, producing and send first instruction execution unit of the action command of carrying out predetermined action.
4. speech recognition equipment according to claim 1 is characterized in that, said second identification module comprises:
Be used for and be sent to the network platform through the voice messaging that said switch module receives, carrying out identification and matching, and receive the 3rd matching unit of the matching result that returns;
When the matching result that is used for receiving when said the 3rd matching unit moves voice messaging for matching, produce and send second instruction execution unit of the action command of carrying out predetermined action.
5. speech recognition equipment according to claim 1 is characterized in that, also comprises:
Be used for the voice messaging that receives is carried out identification and matching,, produce and send the 3rd identification module that the said switch module of control breaks off the closing control instruction of the said voice receiver module and second identification module to switch module when matching when closing voice messaging.
6. speech recognition equipment according to claim 1 is characterized in that, also comprises:
The action recognition module when being used to monitor said action command and being finished, produces and sends the closing control instruction that the said switch module of control breaks off the said voice receiver module and second identification module to switch module.
7. a speech control system comprises action module, it is characterized in that, said system also comprises the arbitrary described speech recognition equipment of claim 1-6; Said action module links to each other with said second identification module, is used for carrying out corresponding actions according to the said action command that receives.
CN 201220120812 2012-03-27 2012-03-27 Speech recognition device and speed control system Expired - Fee Related CN202584717U (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201220120812 CN202584717U (en) 2012-03-27 2012-03-27 Speech recognition device and speed control system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201220120812 CN202584717U (en) 2012-03-27 2012-03-27 Speech recognition device and speed control system

Publications (1)

Publication Number Publication Date
CN202584717U true CN202584717U (en) 2012-12-05

Family

ID=47254105

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201220120812 Expired - Fee Related CN202584717U (en) 2012-03-27 2012-03-27 Speech recognition device and speed control system

Country Status (1)

Country Link
CN (1) CN202584717U (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103680505A (en) * 2013-09-03 2014-03-26 安徽科大讯飞信息科技股份有限公司 Voice recognition method and voice recognition system
CN104954525A (en) * 2014-03-31 2015-09-30 长沙神府智能科技有限公司 Support capable of starting siri function of iphone
WO2015180231A1 (en) * 2014-05-29 2015-12-03 中兴通讯股份有限公司 Voice interaction method and apparatus
WO2015188459A1 (en) * 2014-06-11 2015-12-17 中兴通讯股份有限公司 Terminal control method and device, voice control device and terminal
CN105539359A (en) * 2015-12-09 2016-05-04 上海安吉星信息服务有限公司 Vehicle door control system and engine control system of vehicle and motor vehicle
CN111679594A (en) * 2020-06-24 2020-09-18 四川长虹电器股份有限公司 Far-field voice switch control method and system of visual intelligent product

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103680505A (en) * 2013-09-03 2014-03-26 安徽科大讯飞信息科技股份有限公司 Voice recognition method and voice recognition system
CN104954525A (en) * 2014-03-31 2015-09-30 长沙神府智能科技有限公司 Support capable of starting siri function of iphone
CN104954525B (en) * 2014-03-31 2018-06-05 长沙神府智能科技有限公司 A kind of stent that can start iPhone siri functions
WO2015180231A1 (en) * 2014-05-29 2015-12-03 中兴通讯股份有限公司 Voice interaction method and apparatus
CN105138110A (en) * 2014-05-29 2015-12-09 中兴通讯股份有限公司 Voice interaction method and voice interaction device
WO2015188459A1 (en) * 2014-06-11 2015-12-17 中兴通讯股份有限公司 Terminal control method and device, voice control device and terminal
CN105539359A (en) * 2015-12-09 2016-05-04 上海安吉星信息服务有限公司 Vehicle door control system and engine control system of vehicle and motor vehicle
CN111679594A (en) * 2020-06-24 2020-09-18 四川长虹电器股份有限公司 Far-field voice switch control method and system of visual intelligent product

Similar Documents

Publication Publication Date Title
CN202584717U (en) Speech recognition device and speed control system
WO2017071420A1 (en) Method, apparatus and system for voice communication with smart device
CN102938808B (en) Information method for recording in mobile terminal and device
CN105979324B (en) A kind of method and device of smart television control remote controler microphone
EP3157003B1 (en) Terminal control method and device, voice control device and terminal
CN107886952A (en) A kind of method, apparatus, system and the electronic equipment of Voice command intelligent appliance
CN103210383A (en) Wireless accessory device pairing transfer between multiple host devices
KR20100067274A (en) Intelligent robot and control method thereof
CN109348051A (en) Method, apparatus, equipment and the medium of auto-pickup mobile phone communication
CN105159672A (en) Remote assistance method and client
CN106444454B (en) The energy control method and control device of electricity system
CN103870356A (en) Information processing method and electronic equipment
CN103167128A (en) System and method for achieving automatic sleep of mobile phone based on proximity sensor
CN103235740A (en) Method, system and device for switching among different applications
CN102375918A (en) Interaction virtual role system between facilities
CN103971683A (en) Voice control method and system and handheld device
CN104679239A (en) Terminal input method
CN104657641A (en) Screen locking system with navigation entry function and unlocking method for same
CN105529025A (en) Voice operation input method and electronic device
CN111792465B (en) Elevator control system and method
CN103516906B (en) Device for quickly adding group member on chatting software of mobile equipment
CN104679506A (en) Terminal
CN103218043A (en) Control cancelling method and device
CN107545896A (en) Control method, apparatus and system, the sending method of file and the device of equipment
CN206039831U (en) Voice recognition function's start -up system and remote controller

Legal Events

Date Code Title Description
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20121205

Termination date: 20170327

CF01 Termination of patent right due to non-payment of annual fee