CN104049721B - Information processing method and electronic equipment - Google Patents

Information processing method and electronic equipment Download PDF

Info

Publication number
CN104049721B
CN104049721B CN201310076616.2A CN201310076616A CN104049721B CN 104049721 B CN104049721 B CN 104049721B CN 201310076616 A CN201310076616 A CN 201310076616A CN 104049721 B CN104049721 B CN 104049721B
Authority
CN
China
Prior art keywords
target
unit
voice data
electronic equipment
acquisition
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201310076616.2A
Other languages
Chinese (zh)
Other versions
CN104049721A (en
Inventor
赵方
赵一方
陆游龙
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.)
Lenovo Beijing Ltd
Original Assignee
Lenovo Beijing 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 Lenovo Beijing Ltd filed Critical Lenovo Beijing Ltd
Priority to CN201310076616.2A priority Critical patent/CN104049721B/en
Publication of CN104049721A publication Critical patent/CN104049721A/en
Application granted granted Critical
Publication of CN104049721B publication Critical patent/CN104049721B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The present invention relates to a kind of information processing method and electronic equipments, this method is applied to electronic equipment, the electronic equipment includes sound collection unit, voice recognition unit and recognition unit, this method comprises: obtaining the acquisition information in preset range by the recognition unit, whether the acquisition information is identified to include target object in the determination preset range;When in the preset range including the target object, start voice recognition unit and sound collection unit;Voice data is acquired by the sound collection unit;The voice data of the target object is identified by the voice recognition unit.Speech recognition effect under more people's scenes can be enhanced in information processing method and electronic equipment of the present invention, improves the user experience.

Description

Information processing method and electronic equipment
Technical field
The present invention relates to a kind of information processing technology more particularly to a kind of information processing methods and electronic equipment.
Background technique
Intelligent electronic device at present, the content of carrying is original former more, at present mainly in such a way that remote controler realizes control, But remote-controller function becomes more, and using becoming increasingly complex, user is not easily found it by traditional interactive mode after booting Want content, and learning cost is high, TV interaction ease for use is deteriorated.
It is the main trend of electronic equipment control mode development using voice control, but current voice control mode is more Under people's occasion, when especially more people speak, the voice data of acquisition is more chaotic, is extremely difficult to preferable speech recognition effect, And then lead to not effectively realize voice control.
Summary of the invention
Technical problem to be solved by the invention is to provide a kind of information processing method and electronic equipments, to solve more people The problem of speech recognition effect difference under scape.
In order to solve the above-mentioned technical problems, the present invention provides a kind of information processing method, this method is set applied to electronics Standby, the electronic equipment includes sound collection unit, voice recognition unit and recognition unit, this method comprises:
The acquisition information in preset range is obtained by the recognition unit, the acquisition information is identified with determination It whether include target object in the preset range;
When in the preset range including the target object, start voice recognition unit and sound collection unit;
Voice data is acquired by the sound collection unit;The target object is identified by the voice recognition unit Voice data.
Further, controlling the sound collection unit includes adjusting the pickup zone position of the sound collection unit, is made Pickup zone position adjusted is corresponding with the position of the target object.
Further, in the preset range, the position of the target object is different, and the sound collection unit is adopted Collection direction is different.
Further, the sound collection unit only acquire target object voice data or the sound collection unit Voice data or the voice recognition unit that non-targeted object is deleted after acquisition voice data only identify the voice of target object Data.
Further, in the given time, when not collecting voice data or unfinished speech recognition, institute's predicate is closed Sound recognition unit and the sound collection unit.
Optionally, the recognition unit utilizes camera collection image information, includes multiple objects in described image information, To the acquisition information identified in the determination preset range whether include: comprising target object
Identify prearranged gesture;
Determine that the object for executing the gesture is target object from the multiple object.
In order to solve the above technical problems, the present invention also provides a kind of electronic equipment, the electronic equipment includes:
Recognition unit is identified for obtaining the acquisition information in preset range, and to the acquisition information with determination It whether include target object in the preset range;
Control unit, when in the preset range include the target object when, for start voice recognition unit and Sound collection unit;
Sound collection unit, for acquiring voice;
Acoustic recognition unit, for identification voice data of the target object.
Further, described control unit is also used to control the pickup zone position of the sound collection unit, after making adjustment Pickup zone position it is corresponding with the position of the target object.
Further, in the preset range, the position of the target object is different, and the sound collection unit is adopted Collection direction is different.
Further, the sound collection unit only acquire target object voice data or the sound collection unit Voice data or the voice recognition unit that non-targeted object is deleted after acquisition voice data only identify the voice of target object Data.
Further, in the given time, when not collecting voice data or unfinished speech recognition, the control is single Member is also used to close the voice recognition unit and the sound collection unit.
Further, the recognition unit includes:
Camera includes multiple objects in described image information for acquiring image information,
Gesture recognition module, for identification prearranged gesture;
Target object determining module, for determining that the object for executing the gesture is target object from the multiple object.
Compared with prior art, the application information processing method and electronic equipment can identify target object very accurately, Especially under more people's occasions, the speech recognition effect to target object is enhanced, more accurately realizes and electronic equipment is controlled, from And the influence that other objects in addition to target object control electronic equipment is eliminated, simplify the controlling party of electronic equipment Method, the usage experience for improving user provide a kind of more convenient and fast man-machine interaction mode.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by specification, right Specifically noted structure is achieved and obtained in claim and attached drawing.
Detailed description of the invention
Fig. 1 is the schematic diagram of information processing method embodiment 1 of the present invention;
Fig. 2 is the schematic diagram of information processing method embodiment 1 of the present invention;
Fig. 3,4 be electronic equipment embodiment of the present invention modular structure schematic diagram;
Fig. 5 is the schematic diagram of application example of the present invention.
Attached drawing is used to provide to further understand technical solution of the present invention, and constitutes part of specification, with this The embodiment of application technical solution for explaining the present invention together, does not constitute the limitation to technical solution of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, in the following with reference to the drawings and specific embodiments Technical solution of the present invention is described in further detail, so that those skilled in the art can better understand this hair It is bright and can be practiced, but illustrated embodiment is not as a limitation of the invention.It should be noted that the case where not conflicting Under, the features in the embodiments and the embodiments of the present application can be combined with each other.
Embodiment 1
Information processing method of the present invention is applied to electronic equipment, and the electronic equipment includes that the electronic equipment includes sound Acquisition unit, voice recognition unit and recognition unit, as shown in Figure 1, this method comprises:
Step 101: the acquisition information in preset range being obtained by the recognition unit, the acquisition information is known Not whether to include target object in the determination preset range;
Specifically, in the embodiment, using gesture, specific body as the foundation of identification target object, the identification is single Member acquires image information using dual camera, and certain recognition unit acquires image information, described image using single camera Include multiple objects in information, whether the acquisition information is identified to include target object in the determination preset range Include:
Identify prearranged gesture, body, gesture mentioned here, body can be it is static, be also possible to it is dynamic, such as One hand swings or both hands swing;
Determine that the object for executing the gesture or body is target object from the multiple object.
Step 102: when in the preset range including the target object, starting voice recognition unit and the sound Sound acquisition unit;
Before not starting, the voice recognition unit and sound collection unit do not work.
Step 103: voice data being acquired by the sound collection unit, by described in voice recognition unit identification The voice data of target object.
Optionally, which can be Mike or microphone array.
Microphone array is that multiple Mikes are formed an array according to the topologies that are pre-designed, by collecting Multipath signal carry out space and time diversity processing, different responses can be formed to the signal on different directions, realize that the space of array refers to To characteristic, make up to a certain extent independent Mike can not obtain and using spatial information defect.
In the embodiment, the microphone array is adjustable, then adjust the pickup zone position of the sound collection unit with it is described After the position of target object is corresponding, the voice data of target object is acquired.
Understandably, in the preset range, the position of the target object is different, and the sound collection unit is adopted Collection direction is different.
Outside the acquisition direction of adjustment microphone array namely pickup direction, pickup effective distance can also be adjusted or picked up One or more of the pickups such as sound angle angular dimensions or pickup direction adjust the purpose of the pickup parameter of sound collection unit, It is in order to enable the location of first object information is located at the center in the pickup area of sound collection unit, so as to enhance pair Positioned at the pickup effect of the voice of operator's (sound source) of the position.
The position of target object can be determined based on the collection result of dual camera, and this method is the prior art, herein It repeats no more.The position of target object can be similarly determined based on the collection result of single camera.
Above- mentioned information processing method embodiment 1 mainly determines target object according to acquisition information, namely determines that electronics is set Standby starting object, and then identify the voice data of target object, so that can be set according to the voice data of target object to electronics Standby voice control simplifies electricity to eliminate the influence that other objects in addition to target object control electronic equipment The control method of sub- equipment improves the usage experience of user.
Embodiment 2
Information processing method of the present invention is applied to electronic equipment, and the electronic equipment includes that the electronic equipment includes sound Acquisition unit, voice recognition unit and recognition unit, as shown in Fig. 2, this method comprises:
Step 201: the acquisition information in preset range being obtained by the recognition unit, the acquisition information is known Not whether to include target object in the determination preset range;
Foundation in the embodiment, using the other identifier of face or object as identification target object;
Using face as when the foundation of identification target object, the recognition unit utilizes dual camera or single camera Image information is acquired, includes multiple objects in described image information, identification is carried out to the acquisition information and has determined that described make a reservation for In range whether comprising target object include:
Obtain the face of multiple objects of acquisition;
The face of multiple objects of acquisition is matched one by one with the face of preset target object;
The object of face successful match is determined as target object.
Using other identifier as when the foundation of identification target object, the recognition unit is taken the photograph using dual camera or singly Include multiple objects in described image information as head acquires image information, the acquisition information is carried out described in identification has determined that In preset range whether comprising target object include:
Determine whether each object has preset identifications one by one;
Object with preset identifications is determined as target object.
Understandably, using face or mark as the foundation for determining target object, the preset property with target object is inconvenient In flexibly changing the target object being possessed of control power, and when using certain gestures or body as the foundation for determining target object, then When with multiple objects, as long as the object for executing the certain gestures or body can be used as target object acquisition control.
Step 202: when in the preset range including the target object, starting voice recognition unit and the sound Sound acquisition unit;
Step 203: voice data being acquired by the sound collection unit, by described in voice recognition unit identification The voice data of target object;
In the embodiment, sound collection unit position is fixed, and only collects target object if only target object sounding Voice data, the implementation is fairly simple clear, and details are not described herein;If multiple objects including having except target object are sent out Sound, then in order to achieve the purpose that identify target object voice data following any mode can be used:
The multiple voice data of mode one, acquisition including the voice data of target object, recognition unit is according to object The shape of the mouth as one speaks variation, determine derived from target object the first voice data and non-targeted object second speech data (institute here The second speech data said can be multiple voice data), retain the first voice data or only identifies the first voice of target object Data;
The multiple voice data of mode two, acquisition including the voice data of target object, by multiple voices of acquisition Data are matched with preset vocal print;Only retain or identify the first voice data that there are same characteristic features with preset vocal print;
Mode three only acquires the first voice data for having same characteristic features with preset vocal print, other voice data is made It is eliminated for noise.
Step 204: in the given time, when not collecting voice data or unfinished speech recognition, closing institute's predicate Sound recognition unit and the sound collection unit.
When as described above, using certain gestures or body as the foundation of determining target object, when with multiple objects, As long as the object for executing the certain gestures or body can be used as target object acquisition control.In predetermined time, do not acquire When to voice data or unfinished speech recognition, the voice recognition unit and the sound collection unit are closed, it not only can be with Power consumption is saved, can also be laid the foundation for replacement target object, when using certain gestures or body, as long as new object executes The certain gestures can be identified as new target object, as long as or resetting the i.e. renewable target object of predetermined vocal print, face.
Above- mentioned information processing method embodiment 2 mainly determines target object according to acquisition information, namely determines that electronics is set Standby starting object, and then identify the voice data of target object, so that can be set according to the voice data of target object to electronics Standby voice control simplifies electricity to eliminate the influence that other objects in addition to target object control electronic equipment The control method of sub- equipment, the usage experience for improving user provide a kind of more convenient and fast man-machine interaction mode.
Compared with the existing technology, outstanding information processing method of the present invention can identify that target object speech recognition is imitated very accurately Fruit enhances the speech recognition effect to target object especially under more people's occasions, more accurately realizes and controls electronic equipment
Step shown in the flowchart of the accompanying drawings can be in a computer system such as a set of computer executable instructions It executes.Also, although logical order is shown in flow charts, and it in some cases, can be to be different from herein suitable Sequence executes shown or described step.
In order to realize the above method, the present invention also provides a kind of electronic equipment, as shown in figure 3, the electronic equipment packet It includes:
Recognition unit is identified for obtaining the acquisition information in preset range, and to the acquisition information with determination It whether include target object in the preset range;
Control unit, when in the preset range include the target object when, for start voice recognition unit and Sound collection unit;
Sound collection unit, for acquiring voice;
Acoustic recognition unit, for identification voice data of the target object.
Sound collection unit can position it is adjustable when, described control unit is also used to control picking up for the sound collection unit Sound zone position keeps pickup zone position adjusted corresponding with the position of the target object.
Specifically, in the preset range, the position of the target object is different, the acquisition of the sound collection unit Towards difference.
As it was noted above, can have three ways, such as below at least to realize the identification to the voice data of target object, That is, the sound collection unit only acquire target object voice data or the sound collection unit acquisition voice data after The voice data or the voice recognition unit of deleting non-targeted object only identify the voice data of target object.
Corresponding to embodiment of the method 2, in the given time, when not collecting voice data or unfinished speech recognition, Described control unit is also used to close the voice recognition unit and the sound collection unit.
Optionally, as shown in figure 4, the recognition unit includes:
Dual camera includes multiple objects in described image information for acquiring image information,
Gesture recognition module, for identification prearranged gesture or body;
Target object determining module, for determining that the object for executing the gesture or body is target from the multiple object Object.
Application example
TV is one of most widely used information acquisition instrument of current family, general with informationization technology and network And TV rapidly become family can only information terminal, main clause has the functions such as online, USB flash disk operation, information processing.But electricity Stage depending on being still in traditional button infrared remote control mode in terms of human-computer interaction, it is new to be unable to satisfy information-based bring Human-computer interaction requirement, a kind of more natural, more intelligent man-machine interaction mode become the urgent need of current TV house show, also at For a hot spot of TV operation area research.
Current intelligence TV equipment, the content of carrying is original former more, and user is not easy by traditional interactive mode after booting It finds it and wants content.And remote-controller function becomes greatly, using becoming increasingly complex.Cause learning cost high and TV interaction is easy It is deteriorated with property.
Using the present invention program, dual camera or single camera are added on existing TV and identifier (is realized above The function of middle recognition unit), processor (function of realizing control unit above), speech recognition device (realize above The function of voice recognition unit), microphone array (there is former sound to eliminate and the oriented microphone of sound enhancing function, realize above Sound collection unit function) etc., it can the preferable man-machine interaction mode of usage experience is provided, and realizes control to TV System, as schematically shown in Figure 5.
Specific identification gesture can define, and dual camera and microphone array position have no special requirements, and position is fixed.
Control flow in the application example approximately as:
1, TV initiation gesture, audio monitoring service;
In specific implementation, processor can also wake up the interactive service of TV based on the activation gesture of user.
2, user issues activation gesture (i.e. prearranged gesture);
3, dual camera acquires and outputting video streams are to identifier, and identifier analysis video flowing identifies that user activates hand Gesture determines target object, position and image-forming range of the processor according to dual camera, computed user locations and equipment center line Angle;
4, processor adjusts the main Sounnd source direction of microphone array, and according to the angle, microphone array can be to the user of the direction Voice is enhanced, and the audio-source in other directions carries out Weakening treatment;
5, user inputs gesture or voice;
6, microphone array receives the voice input of user, speech recognition device and gesture recognition to the input of user be intended into Row analysis, processor control TV and execute corresponding movement.
In use above example, TV is started by simple gesture, passes through more natural gesture and voice operating TV Common features, deep layer subfunction can also be evened up by speech recognition, make interaction more naturally succinctly.So that in Duo Renchang Under scape, voice collecting and identification are started according to user's A gesture and is acquired and identifies just for the user A of starting voice.? Voice collecting and identification are closed when the user A of the starting voice no longer has voice input in predetermined time.In other words, of the invention Implement provided by electronic equipment only respond to the phonetic order that is issued of user of starting voice collecting and identification, at this The voice quality of other users under scene not responds.Those skilled in the art should be understood that above-mentioned the application is implemented Device provided by example and/or all or part of the steps in each component part and method of system can be referred to by program Related hardware is enabled to complete, described program can store in computer readable storage medium, such as read-only memory, disk or CD Deng.They can be concentrated on a single computing device, or be distributed over a network of multiple computing devices.It is optional Ground, they can be realized with the program code that computing device can perform.It is thus possible to be stored in storage device by Computing device executes, perhaps they are fabricated to each integrated circuit modules or by them multiple modules or Step is fabricated to single integrated circuit module to realize.In this way, the present invention is not limited to any specific hardware and softwares to combine.
Various units described in the embodiment of the present invention, module are only a kind of examples divided according to its function, Understandably, in the case where system/device/apparatus realizes identical function, those skilled in the art can provide one or more Other function division mode any one or more functional modules can wherein will be filled in specific application using a functional entity It sets or unit realizes that undeniably, the above mapping mode is within the application protection scope.
Although disclosed herein embodiment it is as above, the content only for ease of understanding the present invention and use Embodiment is not intended to limit the invention.Technical staff in any fields of the present invention is taken off not departing from the present invention Under the premise of the spirit and scope of dew, any modification and variation, but the present invention can be carried out in the form and details of implementation Scope of patent protection, still should be subject to the scope of the claims as defined in the appended claims.

Claims (12)

1. a kind of information processing method, this method is applied to electronic equipment, which is characterized in that the electronic equipment includes that sound is adopted Collect unit, voice recognition unit and recognition unit, this method comprises:
The acquisition information in preset range is obtained by the recognition unit, the acquisition information is identified described in determination It whether include target object in preset range, comprising: the face of multiple objects in the recognition unit acquisition preset range;It will The face of multiple objects of acquisition is matched one by one with the face of preset target object;The object of face successful match is true It is set to target object;
Wherein, when with multiple target objects, the object of execution prearranged gesture or body obtains the control of the electronic equipment Power;
When in the preset range including the target object, start voice recognition unit and sound collection unit;
Voice data is acquired by the sound collection unit;The language of the target object is identified by the voice recognition unit Sound data, comprising:
Acquire multiple voice data including the voice data of target object including, by multiple voice data of acquisition with it is preset Vocal print is matched, and is only retained or is identified the voice data for having same characteristic features with the preset vocal print, set with controlling electronics It is standby to execute corresponding movement;
Wherein, it when new object executes prearranged gesture or body, is identified as obtaining the new mesh of the electronic equipment control Object is marked, vocal print is reinitialized.
2. the method as described in claim 1, which is characterized in that controlling the sound collection unit includes adjusting the sound to adopt The pickup zone position for collecting unit, keeps pickup zone position adjusted corresponding with the position of the target object.
3. method according to claim 2, which is characterized in that in the preset range, the position of the target object is not Together, the acquisition direction of the sound collection unit is different.
4. the method as described in claim 1, it is characterised in that: the sound collection unit only acquires the voice number of target object According to or sound collection unit acquisition voice data after delete the voice data or the speech recognition list of non-targeted object Member only identifies the voice data of target object.
5. the method as described in claim 1, it is characterised in that: in the given time, do not collect voice data or not complete When at speech recognition, the voice recognition unit and the sound collection unit are closed.
6. the method as described in claim 1, it is characterised in that: wherein, the recognition unit is believed using camera collection image It ceases, includes multiple objects in described image information;Identify prearranged gesture or body;
When with multiple target objects, determine that the object for executing the prearranged gesture or body is to obtain the electronic equipment The target object of control.
7. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
Recognition unit is identified described in determination for obtaining the acquisition information in preset range, and to the acquisition information It whether include target object in preset range, comprising: the face of multiple objects in the recognition unit acquisition preset range;It will The face of multiple objects of acquisition is matched one by one with the face of preset target object;The object of face successful match is true It is set to target object;
Wherein, when with multiple target objects, the object of execution prearranged gesture or body obtains the control of the electronic equipment Power;
Control unit, when in the preset range including the target object, for starting voice recognition unit and sound Acquisition unit;
Sound collection unit, for acquiring multiple voice data including the voice data of target object;
Acoustic recognition unit, for by acquisition multiple voice data matched with preset vocal print, only retain or identify and The preset vocal print has the voice data of same characteristic features, executes corresponding movement with controlling electronic devices;
Wherein, it when new object executes prearranged gesture or body, is identified as obtaining the new mesh of the electronic equipment control Object is marked, vocal print is reinitialized.
8. electronic equipment as claimed in claim 7, it is characterised in that: described control unit is also used to control the sound collection The pickup zone position of unit keeps pickup zone position adjusted corresponding with the position of the target object.
9. electronic equipment as claimed in claim 8, which is characterized in that in the preset range, the position of the target object Difference is set, the acquisition direction of the sound collection unit is different.
10. electronic equipment as claimed in claim 7, it is characterised in that: the sound collection unit only acquires target object The voice data or the voice of non-targeted object are deleted after voice data or sound collection unit acquisition voice data Recognition unit only identifies the voice data of target object.
11. electronic equipment as claimed in claim 7, it is characterised in that: in the given time, do not collect voice data or When not completing speech recognition, described control unit is also used to close the voice recognition unit and the sound collection unit.
12. electronic equipment as claimed in claim 7, it is characterised in that: the recognition unit includes:
Camera includes multiple objects in described image information for acquiring image information;
Gesture recognition module, for identification prearranged gesture or body;
Target object determining module, for determining pair for executing the prearranged gesture or body when with multiple target objects As the target object to obtain the control of the electronic equipment.
CN201310076616.2A 2013-03-11 2013-03-11 Information processing method and electronic equipment Active CN104049721B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310076616.2A CN104049721B (en) 2013-03-11 2013-03-11 Information processing method and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310076616.2A CN104049721B (en) 2013-03-11 2013-03-11 Information processing method and electronic equipment

Publications (2)

Publication Number Publication Date
CN104049721A CN104049721A (en) 2014-09-17
CN104049721B true CN104049721B (en) 2019-04-26

Family

ID=51502707

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310076616.2A Active CN104049721B (en) 2013-03-11 2013-03-11 Information processing method and electronic equipment

Country Status (1)

Country Link
CN (1) CN104049721B (en)

Families Citing this family (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107004426B (en) * 2014-11-28 2020-09-11 华为技术有限公司 Method and mobile terminal for recording sound of video object
CN105867595A (en) * 2015-01-21 2016-08-17 武汉明科智慧科技有限公司 Human-machine interaction mode combing voice information with gesture information and implementation device thereof
CN104657105B (en) * 2015-01-30 2016-10-26 腾讯科技(深圳)有限公司 A kind of method and apparatus of the speech voice input function opening terminal
CN106325481A (en) * 2015-06-30 2017-01-11 展讯通信(天津)有限公司 A non-contact type control system and method and a mobile terminal
CN105205454A (en) * 2015-08-27 2015-12-30 深圳市国华识别科技开发有限公司 System and method for capturing target object automatically
CN106887229A (en) * 2015-12-16 2017-06-23 芋头科技(杭州)有限公司 A kind of method and system for lifting the Application on Voiceprint Recognition degree of accuracy
CN106095340A (en) * 2016-06-14 2016-11-09 深圳市国华识别科技开发有限公司 Gage data stores method and apparatus
CN107135445A (en) * 2017-03-28 2017-09-05 联想(北京)有限公司 A kind of information processing method and electronic equipment
CN107180632A (en) * 2017-06-19 2017-09-19 微鲸科技有限公司 Sound control method, device and readable storage medium storing program for executing
WO2019061285A1 (en) * 2017-09-29 2019-04-04 深圳传音通讯有限公司 Video recording method and video recording system of intelligent terminal
CN109696658A (en) * 2017-10-23 2019-04-30 京东方科技集团股份有限公司 Acquire equipment, sound collection method, audio source tracking system and method
CN109961781A (en) * 2017-12-22 2019-07-02 深圳市优必选科技有限公司 Voice messaging method of reseptance, system and terminal device based on robot
CN108052818B (en) * 2017-12-28 2020-11-13 Oppo广东移动通信有限公司 Application starting method and device, storage medium and electronic equipment
CN110121048A (en) * 2018-02-05 2019-08-13 青岛海尔多媒体有限公司 The control method and control system and meeting all-in-one machine of a kind of meeting all-in-one machine
CN108831451B (en) * 2018-03-30 2020-12-29 广东思派康电子科技有限公司 Computer readable storage medium and voice recognition sound box using same
CN110797021A (en) * 2018-05-24 2020-02-14 腾讯科技(深圳)有限公司 Hybrid speech recognition network training method, hybrid speech recognition device and storage medium
CN108831462A (en) * 2018-06-26 2018-11-16 北京奇虎科技有限公司 Vehicle-mounted voice recognition methods and device
CN109147787A (en) * 2018-09-30 2019-01-04 深圳北极鸥半导体有限公司 A kind of smart television acoustic control identifying system and its recognition methods
CN109817211B (en) * 2019-02-14 2021-04-02 珠海格力电器股份有限公司 Electric appliance control method and device, storage medium and electric appliance
CN110197171A (en) * 2019-06-06 2019-09-03 深圳市汇顶科技股份有限公司 Exchange method, device and the electronic equipment of action message based on user
CN110223690A (en) * 2019-06-10 2019-09-10 深圳永顺智信息科技有限公司 The man-machine interaction method and device merged based on image with voice
CN110366065A (en) * 2019-07-24 2019-10-22 长沙世邦通信技术有限公司 Orientation follows the method, apparatus, system and storage medium of face location pickup
CN110364176A (en) * 2019-08-21 2019-10-22 百度在线网络技术(北京)有限公司 Audio signal processing method and device

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101046958A (en) * 2006-03-29 2007-10-03 株式会社东芝 Apparatus and method for speech processing
CN102945672A (en) * 2012-09-29 2013-02-27 深圳市国华识别科技开发有限公司 Voice control system for multimedia equipment, and voice control method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101046958A (en) * 2006-03-29 2007-10-03 株式会社东芝 Apparatus and method for speech processing
CN102945672A (en) * 2012-09-29 2013-02-27 深圳市国华识别科技开发有限公司 Voice control system for multimedia equipment, and voice control method

Also Published As

Publication number Publication date
CN104049721A (en) 2014-09-17

Similar Documents

Publication Publication Date Title
CN107210033B (en) Updating language understanding classifier models for digital personal assistants based on crowd sourcing
CN105323648B (en) Caption concealment method and electronic device
JP2020500330A (en) Focus session in voice interface device
JP2020144375A (en) System control method, system, and program
US10664060B2 (en) Multimodal input-based interaction method and device
CN106415719B (en) It is indicated using the steady endpoint of the voice signal of speaker identification
US10318016B2 (en) Hands free device with directional interface
CN107408027B (en) Information processing apparatus, control method, and program
KR101726945B1 (en) Reducing the need for manual start/end-pointing and trigger phrases
EP2766790B1 (en) Authenticated gesture recognition
US10796693B2 (en) Modifying input based on determined characteristics
CN104982041B (en) For controlling the portable terminal and its method of hearing aid
JP6739907B2 (en) Device specifying method, device specifying device and program
US20150370474A1 (en) Multiple view interface for video editing system
US9389681B2 (en) Sensor fusion interface for multiple sensor input
WO2018036149A1 (en) Multimedia interactive teaching system and method
US10453461B1 (en) Remote execution of secondary-device drivers
US10438080B2 (en) Handwriting recognition method and apparatus
US9129478B2 (en) Attributing user action based on biometric identity
WO2018152012A1 (en) Associating semantic identifiers with objects
CN107370649B (en) Household appliance control method, system, control terminal and storage medium
CN107340991B (en) Voice role switching method, device, equipment and storage medium
US8744528B2 (en) Gesture-based control method and apparatus of an electronic device
US20200016745A1 (en) Data Processing Method for Care-Giving Robot and Apparatus
US20150088515A1 (en) Primary speaker identification from audio and video data

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant