CN108600810A - The television system and method for precision of identifying speech are improved using voice remote controller - Google Patents

The television system and method for precision of identifying speech are improved using voice remote controller Download PDF

Info

Publication number
CN108600810A
CN108600810A CN201810414812.9A CN201810414812A CN108600810A CN 108600810 A CN108600810 A CN 108600810A CN 201810414812 A CN201810414812 A CN 201810414812A CN 108600810 A CN108600810 A CN 108600810A
Authority
CN
China
Prior art keywords
voice
remote controller
speech
transmission module
module
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
Application number
CN201810414812.9A
Other languages
Chinese (zh)
Inventor
邹文婷
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.)
Sichuan Changhong Electric Co Ltd
Original Assignee
Sichuan Changhong Electric 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 Sichuan Changhong Electric Co Ltd filed Critical Sichuan Changhong Electric Co Ltd
Priority to CN201810414812.9A priority Critical patent/CN108600810A/en
Publication of CN108600810A publication Critical patent/CN108600810A/en
Pending legal-status Critical Current

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/41Structure of client; Structure of client peripherals
    • H04N21/422Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
    • H04N21/42203Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS] sound input device, e.g. microphone
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/26Speech to text systems
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/41Structure of client; Structure of client peripherals
    • H04N21/422Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Signal Processing (AREA)
  • Selective Calling Equipment (AREA)

Abstract

The invention discloses a kind of television system and method improving precision of identifying speech using voice remote controller, which includes voice remote controller and smart television;The voice remote controller includes remote controller body, and the first transmission module being connected with each other and several microphones are equipped in remote controller body;The second transmission module, microphone array and speech processing algorithm module are equipped in the smart television, the speech processing algorithm module is connected with the second transmission module and microphone array respectively, and the first transmission module is communicated to connect with the second transmission module.The system and method for the present invention forms distributive array microphone using the microphone array built in the microphone and smart television built in TV remote controller, distributive array microphone is allow to cover the area of bigger, more voice and ambient sound original recording data are provided, to promote the precision and efficiency of Speech processing.

Description

The television system and method for precision of identifying speech are improved using voice remote controller
Technical field
The present invention relates to far field voice technology fields, more particularly to voice remote controller is utilized to improve the electricity of precision of identifying speech Viewing system and method.
Background technology
In recent years along with the development of artificial intelligence, the mode of human-computer interaction is also changing.It introduces more natural Far field interactive voice, it has also become the development trend and widespread demand of numerous Intelligent hardwares such as TV, air-conditioning.But technically come It sees, far field voice there is also some problems, such as face the different sound field rings such as sales field, household using the various product of the technology The distance of the border and sound source distance microphone array usage scenarios such as farther out, can cause discrimination relatively low, manipulation precision is not as good as close Field voice.And appearance and modeling, the assembly technology etc. of consumer level products again limit the quantity of microphone and the distributional pattern of array.
Its problem may be summarized as follows:
1, due to television set form-making design, assembly difficulty etc., number of microphone and the arrangement side of array are formed Formula is limited, the linear array of generally 2MIC or 4MIC, therefore there is television set microphone activity ratio, discrimination are lower Problem.
2, the MIC built in TV and user distance farther out when, the noise for recording voice is relatively low, algorithm process difficulty Greatly, cause television set less efficient when analyzing voice messaging input by user.
3, the MIC built in TV is closer from TV the machine loudspeaker, and the voice signal for being recorded to the broadcasting of TV the machine is stronger, shadow Ring the voice input operation of user.
Invention content
It is insufficient in above-mentioned background technology the purpose of the present invention is overcoming, it provides and improves speech recognition essence using voice remote controller The television system and method for degree are formed using the microphone array built in the microphone and smart television built in TV remote controller Distributive array microphone so that distributive array microphone can cover the area of bigger, provide more voice and environment Sound original recording data, to promote the precision and efficiency of Speech processing.
In order to reach above-mentioned technique effect, the present invention takes following technical scheme:
The television system that precision of identifying speech is improved using voice remote controller, including voice remote controller and smart television;Institute It includes remote controller body to state voice remote controller, and the first transmission module being connected with each other and several wheats are equipped in remote controller body Gram wind;The second transmission module, microphone array and speech processing algorithm module, the speech processes are equipped in the smart television Algoritic module is connected with the second transmission module and microphone array respectively;Wherein, first transmission module and the second transmission mould Block communicates to connect, and the first transmission module is used for the collected transmitting voice signal of microphone to the second transmission module;Second The transmitting voice signal that transmission module is used to receive is to speech processing algorithm module, and microphone array is for acquiring voice signal And it is transmitted to speech processing algorithm module, speech processing algorithm module is for handling the voice signal received;
In the television system for improving precision of identifying speech using voice remote controller of the present invention, voice remote controller is utilized Microphone constitutes distributed microphone array with television internal microphone array, and the microphone of voice remote controller is as distribution The sound that microphone receives can be transferred to smart television by one of formula microphone array subarray by transmission module In so that the speech processing algorithm module of smart television increases when handling the data of smart television built-in microphone array input The voice data that remote controller comes is added to carry out calculation processing, to provide additional number for speech processing algorithm module According to can reduce speech recognition difficulty, improve precision of identifying speech.
Further, the remote controller body is equipped with the voice key of the microphone on opening remote control device ontology, in user When not pressing voice key, then the near field voice function of television system is only opened, i.e., only television internal microphone array carries out language Sound acquires, when user presses voice key, then microphone that can be on opening remote control device ontology carries out voice collecting, i.e. remote controler Microphone is carried out at the same time voice collecting with array microphone array built in TV.
Further, first transmission module uses double-direction radio to transmit to when the second transmission module transmission of speech signals Mode.
Further, first transmission module to when the second transmission module transmission of speech signals use Bluetooth transmission mode Or 2.4G transmission modes.
Further, the speech processing algorithm module at least carries out noise suppressed to the voice signal received, echo is supported Disappear, the processing of signal enhancing.
Meanwhile the invention also discloses a kind of methods improving precision of identifying speech using voice remote controller, including above-mentioned Using voice remote controller improve precision of identifying speech television system, specifically comprise the steps of:
S1. communication connection is established between the first transmission module and the second transmission module;
S2. the microphone in the microphone array and voice remote controller in smart television is carried out at the same time adopting for voice signal Collection;
S3. the transmitting voice signal of acquisition to speech processing algorithm module, voice remote controller are passed through by microphone array The transmitting voice signal that one transmission module acquires microphone is to speech processing algorithm module;
S4. speech processing algorithm module handles the voice signal received.
Further, the connection established between the first transmission module and the second transmission module in the step S1 is wireless blue Tooth connects or less radio-frequency connection.
Further, the remote controller body is equipped with the voice key of the microphone on opening remote control device ontology, and only exists When user presses voice key, the microphone on remote controller body just starts to collect voice signal.
Further, speech processing algorithm module at least carries out noise suppression to the voice signal received in the step S4 The processing of system, echo cancelltion, signal enhancing.
Compared with prior art, the present invention having advantageous effect below:
In the television system for improving precision of identifying speech using voice remote controller of the present invention, voice remote controller and electricity are utilized Distributed microphone array is constituted depending on machine built-in microphone array, relative to the microphone array of current centralization, the section of array Point can cover the area of bigger, remote controler as one of array nodal distance sound source closer to recording signal-to-noise ratio is substantially Degree is promoted, and algorithm process difficulty can also reduce, and the effect of overall signal processing also has the promotion of highly significant, can effectively carry Rise the usage experience of user.
Description of the drawings
Fig. 1 is the signal of the television system that precision of identifying speech is improved using voice remote controller of one embodiment of the invention Figure.
Fig. 2 is that the method flow that precision of identifying speech is improved using voice remote controller of one embodiment of the invention is illustrated Figure.
Specific implementation mode
With reference to the embodiment of the present invention, the invention will be further elaborated.
Embodiment:
Embodiment one:
As shown in Figure 1, a kind of television system improving precision of identifying speech using voice remote controller, including voice remote controller And smart television.
The voice remote controller includes remote controller body, and the first transmission mould being connected with each other is equipped in remote controller body Block and several microphones;The voice key of the microphone on opening remote control device ontology is equipped on remote controller body.
The second transmission module, microphone array and speech processing algorithm module, the voice are equipped in the smart television Processing Algorithm module is connected with the second transmission module and microphone array respectively.
Wherein, first transmission module is communicated to connect with the second transmission module, and the first transmission module is used for Mike The collected transmitting voice signal of wind is to the second transmission module;Second transmission module for will the transmitting voice signal that receive to language Sound Processing Algorithm module, microphone array for acquiring voice signal and being transmitted to speech processing algorithm module, calculate by speech processes Method module specifically increases in noise suppressed, echo cancelltion, signal enhancing etc. and calculates for handling the voice signal received Data, to improve accuracy of identification.
Wherein, described when user does not press voice key, then only open the near field voice function of television system, i.e. only TV Machine built-in microphone array carries out voice collecting, when user presses voice key, then microphone that can be on opening remote control device ontology Voice collecting is carried out, i.e. array microphone array built in the microphone and TV of remote controler is carried out at the same time voice collecting.
Specifically, first transmission module to when the second transmission module transmission of speech signals use double-direction radio transmission side Formula.Such as Bluetooth transmission mode or 2.4G transmission modes, in the present embodiment, the first transmission module is by indigo plant to the second transmission module The bluetooth module that tooth device is constituted then specifically uses Bluetooth transmission mode when transmission of speech signals.
In the television system for improving precision of identifying speech using voice remote controller of the present invention, voice remote controller is utilized Microphone constitutes distributed microphone array with television internal microphone array, and the microphone of voice remote controller is as distribution The sound that microphone receives can be transferred to smart television by one of formula microphone array subarray by transmission module In so that the speech processing algorithm module of smart television increases when handling the data of smart television built-in microphone array input The voice data that remote controller comes is added to carry out calculation processing, to provide additional number for speech processing algorithm module According to can reduce speech recognition difficulty, improve precision of identifying speech.
Embodiment two
As shown in Fig. 2, a kind of method improving precision of identifying speech using voice remote controller, including above-mentioned utilizes voice Remote controler improves the television system of precision of identifying speech, specifically comprises the steps of:
S1. wireless blue tooth connection or less radio-frequency connection are established between the first transmission module and the second transmission module;This implementation Example connects to establish wireless blue tooth.
S2. the microphone in the microphone array and voice remote controller in smart television is carried out at the same time adopting for voice signal Collection;
S3. the transmitting voice signal of acquisition to speech processing algorithm module, voice remote controller are passed through by microphone array The transmitting voice signal that one transmission module acquires microphone is to speech processing algorithm module;
S4. speech processing algorithm module is handled the voice signal received comprising noise suppressed, echo are supported Disappear, the processing of signal enhancing etc..
Preferably, the voice key for the microphone that can be arranged on the remote controller body on opening remote control device ontology, and Only when user presses voice key, the microphone on remote controller body just starts to collect voice signal.
It is understood that the principle that embodiment of above is intended to be merely illustrative of the present and the exemplary implementation that uses Mode, however the present invention is not limited thereto.For those skilled in the art, in the essence for not departing from the present invention In the case of refreshing and essence, various changes and modifications can be made therein, these variations and modifications are also considered as protection scope of the present invention.

Claims (9)

1. improving the television system of precision of identifying speech using voice remote controller, which is characterized in that include voice remote controller and intelligence It can TV;The voice remote controller includes remote controller body, and the first transmission mould being connected with each other is equipped in remote controller body Block and several microphones;The second transmission module, microphone array and speech processing algorithm module, institute are equipped in the smart television Speech processing algorithm module is stated respectively to be connected with the second transmission module and microphone array;
Wherein, first transmission module is communicated to connect with the second transmission module, and the first transmission module is used for Mike's elegance The transmitting voice signal collected is to the second transmission module;At the transmitting voice signal to voice that second transmission module is used to receive Algoritic module is managed, microphone array is for acquiring voice signal and being transmitted to speech processing algorithm module, speech processing algorithm mould Block is for handling the voice signal received.
2. the television system according to claim 1 for improving precision of identifying speech using voice remote controller, which is characterized in that The remote controller body is equipped with the voice key of the microphone on opening remote control device ontology.
3. the television system according to claim 1 for improving precision of identifying speech using voice remote controller, which is characterized in that First transmission module to when the second transmission module transmission of speech signals use double-direction radio transmission mode.
4. the television system according to claim 3 for improving precision of identifying speech using voice remote controller, which is characterized in that First transmission module to when the second transmission module transmission of speech signals use Bluetooth transmission mode or 2.4G transmission modes.
5. the television system according to claim 1 for improving precision of identifying speech using voice remote controller, which is characterized in that The speech processing algorithm module at least carries out the voice signal received the processing of noise suppressed, echo cancelltion, signal enhancing.
6. the method for improving precision of identifying speech using voice remote controller, including utilizing voice remote control as described in claim 1 Device improves the television system of precision of identifying speech, which is characterized in that specifically comprises the steps of:
S1. communication connection is established between the first transmission module and the second transmission module;
S2. the microphone in the microphone array and voice remote controller in smart television is carried out at the same time the acquisition of voice signal;
S3. microphone array passes the transmitting voice signal of acquisition to speech processing algorithm module, voice remote controller by first The transmitting voice signal that defeated module acquires microphone is to speech processing algorithm module;
S4. speech processing algorithm module handles the voice signal received.
7. the method according to claim 6 for improving precision of identifying speech using voice remote controller, which is characterized in that described The connection established between the first transmission module and the second transmission module in step S1 is that wireless blue tooth connects or less radio-frequency connects.
8. the method according to claim 6 for improving precision of identifying speech using voice remote controller, which is characterized in that described Remote controller body is equipped with the voice key of the microphone on opening remote control device ontology, and only when user presses voice key, remote control Microphone on device ontology just starts to collect voice signal.
9. the method according to claim 6 for improving precision of identifying speech using voice remote controller, which is characterized in that described Speech processing algorithm module at least carries out noise suppressed, echo cancelltion, signal enhancing to the voice signal that receives in step S4 Processing.
CN201810414812.9A 2018-05-03 2018-05-03 The television system and method for precision of identifying speech are improved using voice remote controller Pending CN108600810A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810414812.9A CN108600810A (en) 2018-05-03 2018-05-03 The television system and method for precision of identifying speech are improved using voice remote controller

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810414812.9A CN108600810A (en) 2018-05-03 2018-05-03 The television system and method for precision of identifying speech are improved using voice remote controller

Publications (1)

Publication Number Publication Date
CN108600810A true CN108600810A (en) 2018-09-28

Family

ID=63620515

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810414812.9A Pending CN108600810A (en) 2018-05-03 2018-05-03 The television system and method for precision of identifying speech are improved using voice remote controller

Country Status (1)

Country Link
CN (1) CN108600810A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109767766A (en) * 2019-01-23 2019-05-17 海信集团有限公司 A kind of audio recognition method and device
CN110121091A (en) * 2019-04-24 2019-08-13 珠海东之尼电子科技有限公司 A kind of control method and equipment of wireless speech remote controler
WO2021004511A1 (en) * 2019-07-11 2021-01-14 海信视像科技股份有限公司 Electronic device, non-volatile storage medium, and voice recognition method
CN113422992A (en) * 2021-06-17 2021-09-21 歌尔股份有限公司 Remote controller and electronic system

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020072912A1 (en) * 2000-07-28 2002-06-13 Chih-Chuan Yen System for controlling an apparatus with speech commands
CN103187063A (en) * 2011-12-30 2013-07-03 三星电子株式会社 Electronic apparatus and method of controlling electronic apparatus
CN104780411A (en) * 2015-03-20 2015-07-15 无锡华海天和信息科技有限公司 Television box remote controller with voice control function, system and using method
CN205071171U (en) * 2015-11-03 2016-03-02 Tcl集团股份有限公司 Intelligent television
CN206490770U (en) * 2016-11-30 2017-09-12 深圳市岚正科技有限公司 There is the set top box and set-top-box system of far field and near field voice identification simultaneously
CN107845388A (en) * 2017-12-25 2018-03-27 青岛海信移动通信技术股份有限公司 Audio recognition method and device

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020072912A1 (en) * 2000-07-28 2002-06-13 Chih-Chuan Yen System for controlling an apparatus with speech commands
CN103187063A (en) * 2011-12-30 2013-07-03 三星电子株式会社 Electronic apparatus and method of controlling electronic apparatus
CN104780411A (en) * 2015-03-20 2015-07-15 无锡华海天和信息科技有限公司 Television box remote controller with voice control function, system and using method
CN205071171U (en) * 2015-11-03 2016-03-02 Tcl集团股份有限公司 Intelligent television
CN206490770U (en) * 2016-11-30 2017-09-12 深圳市岚正科技有限公司 There is the set top box and set-top-box system of far field and near field voice identification simultaneously
CN107845388A (en) * 2017-12-25 2018-03-27 青岛海信移动通信技术股份有限公司 Audio recognition method and device

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109767766A (en) * 2019-01-23 2019-05-17 海信集团有限公司 A kind of audio recognition method and device
CN110121091A (en) * 2019-04-24 2019-08-13 珠海东之尼电子科技有限公司 A kind of control method and equipment of wireless speech remote controler
WO2021004511A1 (en) * 2019-07-11 2021-01-14 海信视像科技股份有限公司 Electronic device, non-volatile storage medium, and voice recognition method
CN112243588A (en) * 2019-07-11 2021-01-19 海信视像科技股份有限公司 Electronic device, nonvolatile storage medium, and voice recognition method
JP2021015180A (en) * 2019-07-11 2021-02-12 東芝映像ソリューション株式会社 Electronic apparatus, program and voice recognition method
JP7216621B2 (en) 2019-07-11 2023-02-01 Tvs Regza株式会社 Electronic devices, programs and speech recognition methods
CN113422992A (en) * 2021-06-17 2021-09-21 歌尔股份有限公司 Remote controller and electronic system
CN113422992B (en) * 2021-06-17 2023-03-21 歌尔股份有限公司 Remote controller and electronic system

Similar Documents

Publication Publication Date Title
CN108600810A (en) The television system and method for precision of identifying speech are improved using voice remote controller
CN104735598B (en) Hearing aid system and voice acquisition method of hearing aid system
CN106910500B (en) Method and device for voice control of device with microphone array
CN103686575B (en) Auditory prosthesis
CN208227260U (en) A kind of smart bluetooth earphone and bluetooth interactive system
CN101778330B (en) Mobile phone platform-based array microphone hearing aid and control method thereof
CN108320749A (en) Far field voice control device and far field speech control system
CN203279119U (en) Wireless earphone based on motion sensor
CN107105359A (en) One kind switching earphone mode of operation method and a kind of earphone
CN206559550U (en) The remote control and television system of a kind of built-in microphone array
CN110022401A (en) A kind of control parameter setting method, terminal and computer readable storage medium
CN108600496A (en) Electronic equipment and its control method
CN107205187A (en) A kind of method, device and terminal device based on earphone control music
CN107680594A (en) A kind of distributed intelligence voice collecting identifying system and its collection and recognition method
CN108923810A (en) Interpretation method and relevant device
CN103856870A (en) Method of processing sound and hearing apparatus using the same
CN109218503A (en) Directional loudspeaker, mobile terminal radiation protection system and method
CN109754796A (en) The method and electronic device of function are executed using multiple microphones
CN104850278A (en) Non-contact control integrated machine and control method implemented by same
CN201585128U (en) Array microphone hearing-aid based on mobile phone platform
CN106409306A (en) Intelligent system obtaining human voice and obtaining method based on the system
CN106328154A (en) Front-end audio processing system
CN208538475U (en) A kind of intelligent robot
CN108882112B (en) Audio playing control method and device, storage medium and terminal equipment
CN103167197B (en) Method and terminal with functions of shared voice frequency noise reduction and echo cancellation

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180928