CN208724111U - Far field speech control system based on television equipment - Google Patents
Far field speech control system based on television equipment Download PDFInfo
- Publication number
- CN208724111U CN208724111U CN201820976245.1U CN201820976245U CN208724111U CN 208724111 U CN208724111 U CN 208724111U CN 201820976245 U CN201820976245 U CN 201820976245U CN 208724111 U CN208724111 U CN 208724111U
- Authority
- CN
- China
- Prior art keywords
- module
- far field
- television equipment
- audio signal
- control system
- 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
Links
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The utility model relates to speech recognition technologies, the utility model is to solve the problems, such as that existing far field speech control system identification phonetic order precision is not high, provide a kind of far field speech control system based on television equipment, its technical solution can be summarized as: the far field speech control system based on television equipment, including far field pickup module, audio signal separation module, coded treatment module and control module, the far field pickup module, audio signal separation module, coded treatment module and control module are sequentially connected, the audio signal separation module is connect with control module, the audio signal of environmental noise and television equipment loudspeaker in audio signal separation module separation acquisition audio signal, obtain clean human voice signal, to improve the accuracy of far field voice control, especially suitable for the intelligent terminal in domestic environment.
Description
Technical field
The utility model relates to technical field of voice recognition, more particularly to a kind of voice control based on television equipment
System.
Background technique
With the fast development of artificial intelligence technology, will be used wider and wider, application scenarios are more and more diversified,
In most important one side be exactly speech recognition technology, near field voice identification technology is mature, and recognition accuracy is high, but needs to lean on
Nearly pickup module within the scope of certain distance and operates speech trigger device, therefore, under intelligentized trend, far field voice control
Technology processed is come into being, and which gets rid of trigger device using speech trigger, and can interact at a distance.
But in actual use, since there are a large amount of noises, including environmental noise and equipment loudspeaking in environment
The sound of device is easy to happen maloperation under the influence of noise using equipment such as far field voice technology control television set, set-top boxes
Or do not operate, in the prior art, generallys use and simple amplification filtering processing is carried out to audio signal, can reach so certain
Noise reduction effect cause television equipment identification voice to refer to but in addition to phonetic order can also remain many noises in audio signal
It enables precision not high, influences user experience.
Utility model content
The technical problem to be solved by the utility model is to proposing a kind of far field voice control system based on television equipment
It is not high to be able to solve existing far field speech control system identification phonetic order precision after it joined corresponding software approach for system
Problem.
The utility model solves technical solution used by above-mentioned technical problem: the far field voice control based on television equipment
System processed, including far field pickup module, audio signal separation module, coded treatment module and control module, the far field pickup
Module, audio signal separation module, coded treatment module and control module are sequentially connected, the audio signal separation module and control
The connection of molding block.
Specifically, the far field pickup module is microphone array, the microphone array includes diamylose array, bar shaped four
Wheat array and annular six wheat arrays.
Specifically, the microphone array is classified as digital microphone array.
Alternatively, the microphone array is classified as simulation microphone array;
The audio signal separation module includes AD conversion unit, the AD conversion unit and simulation microphone array
Connection.
Further, the microphone array is set to inside television equipment, is located at television equipment bottom or top and is hit exactly
Between position.
Further, the control module further includes standby controllable interface, the standby controllable interface and coded treatment mould
Block connection;
Specifically, the television equipment includes digital television or set-top box.
The beneficial effects of the utility model are: the far field voice control system described in the utility model based on television equipment
System passes through above-mentioned audio signal separation module and coded treatment module, after application corresponding software method, audio signal splitting die
The audio signal that the audio signal and loudspeaker that root tuber is sent according to control module are sent, separate the environmental noise in voice signal with
And the audio signal of television equipment, echo cancellation, auditory localization, Wave beam forming and noise Reverberation Rejection etc. are then carried out to it again
Simple human voice signal is obtained after algorithm process, control precision is higher, and television equipment can identify user when speaking, if be
The phonetic order sent to it reduces the maloperation of television equipment, and under television equipment ideal case, user is without triggering remote control
The booting of the activation to television equipment can be realized in device.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the utility model embodiment.
Specific embodiment
The embodiments of the present invention is described in detail below in conjunction with attached drawing.
Far field speech control system described in the utility model based on television equipment, including audio signal separation module and
Control module connected to it is applying corresponding software method by above-mentioned audio signal separation module and coded treatment module
Afterwards, the audio signal that the audio signal and loudspeaker that audio signal separation module is sent according to control module are sent, separates voice
Then the audio signal of environmental noise and television equipment in signal carries out echo cancellation, auditory localization, wave beam shape to it again
At and the processing of noise Reverberation Rejection scheduling algorithm after obtain simple human voice signal, coded treatment module identifies the language in audio signal
Sound instructs and is sent to control module, and control module executes the corresponding operation of phonetic order, realizes the accurate control to television equipment
System.
Embodiment
The far field speech control system based on television equipment of the utility model embodiment, as shown in Figure 1, being picked up including far field
Sound module 100, audio signal separation module 200, coded treatment module and control module 400, the far field pickup module 100,
Audio signal separation module 200, coded treatment module and control module 400 are sequentially connected, the audio signal separation module 200
It is connect with control module 400;After application corresponding software method, audio signal is by 200 noise reduction of audio signal separation module point
After processing, it is sent to coded treatment module, coded treatment module includes voice recognition unit and natural language processing unit, is compiled
Code processing module the phonetic order in audio signal and is sent to control module 400 for identification, and control module 400 receives voice
Matching response is operated and is executed in instruction database after instruction.
It in the present embodiment, include triggering phonetic order in above-mentioned control module 400, coded treatment module includes that voice swashs
Unit living, after application corresponding software method, in the environment that someone talks, television equipment can distinguish user talk or
User sends phonetic control command to it, and user can like default triggering phonetic order according to itself, for example, default triggering language
Sound instruction is " small electricity ", and control module 400 is only after receiving triggering phonetic order " small electricity ", after coded treatment module just receives
Continuous audio signal, control module 400 just respond subsequent operation, and in actual use, user is intended to control television equipment
When processed, " small electricity " first need to be said to television equipment and activated, phonetic control command is retransmited after activation and is operated on it.
Above-mentioned audio signal separation module 200 includes noise reduction unit, echo cancellation unit, auditory localization unit, wave beam shape
At unit and noise Reverberation Rejection unit.Noise reduction unit is used to amplify the audio signal of acquisition filtering processing, audio letter
Number separation module 200 is connect with control module 400, and on the basis of application corresponding software method, control module 400 sets TV
The audio signal of standby loudspeaker is sent to audio signal separation module 200, and audio signal separation module 200 is to containing phonetic order
And the audio signal of television equipment loudspeaker audio is separated, then carry out again echo cancellation, auditory localization, Wave beam forming and
Simple human voice signal is obtained after the processing of noise Reverberation Rejection scheduling algorithm, and sends it to coded treatment module, coded treatment
Module obtains phonetic order after carrying out ASR (speech recognition) and NLP (natural language processing) scheduling algorithm to it, and is sent to control
Module 400 executes the corresponding operation of phonetic order.
Preferably, above-mentioned far field pickup module 100 is microphone array, and microphone array includes diamylose array, bar shaped four
The forms such as wheat array and annular six wheat arrays, difference between the phase of the sound wave received using multiple microphones to sound wave into
Row filtering, ambient background noise can be disposed, comprehensively consider television equipment design and speech performance etc. to greatest extent
Aspect mainly uses four wheat array of bar shaped.
Microphone includes digital microphone and simulation microphone, in the present embodiment, a kind of embodiment: according to number
Microphone array can directly be connect with audio signal separation module 200;Another embodiment: according to simulation microphone array
Column, are connect by AD conversion unit with audio signal separation module 200.
Preferably, above-mentioned microphone array is set to inside television equipment, is located at television equipment bottom or top middle
Position is arranged inside television equipment, and integrated design reduces aerial lug, keeps whole system appearance more concise and beautiful, separately
Outside, microphone array can also receive the audio signal of television equipment loudspeaker pass, in order to believe the loudspeaker audio received
Number symmetrically, microphone array is set to television equipment bottom or top middle position, audio signal separation module
200, which are sent to audio signal separation module 200 according to the audio signal and control module 400 of the loudspeaker received, believes audio
It number is separated.
In the present embodiment, control module 400 further includes standby controllable interface, standby controllable interface and coded treatment module
Connection, on the basis of application corresponding software method, when television equipment is in standby, control module 400 is in standby
State, microphone array 100, audio signal separation module 200 and coded treatment module are in normal operating conditions, control
Module includes that default wake up instruction is sent to audio signal point after microphone array 100 obtains the default wake up instruction of user's sending
From module 200, coded treatment module, after the processing such as separating, identifying, it is sent to control module, control module 400 obtains pre-
If being waken up after wake up instruction, television equipment can be waken up by realizing user without triggering remote control voice device.
Television equipment in the present embodiment can be digital television, set-top box or other Intelligent hardware terminals, pass through
This system, application corresponding software method after, it can be achieved that Intelligent hardware terminal far field voice control, and Intelligent hardware terminal know
Other precision is higher, is not susceptible to maloperation or does not operate, and promotes user experience.
It should be noted that provided by the utility model is only a kind of far field speech control system based on television equipment
Specific structure, the correlation module being related in the system is hardware system module or for computer software in the prior art
The functional module that program or agreement are combined with hardware, the sheet of computer software programs or agreement involved by the functional module
The technology that body is well known to those skilled in the art is not the improvements of this system, and details are not described herein again;This system changes
Into the interaction relationship or connection relationship between each module, as the whole construction of system is improved, to solve
This system relevant art problem to be solved.
Claims (7)
1. the far field speech control system based on television equipment, which is characterized in that separated including far field pickup module, audio signal
Module, coded treatment module and control module, the far field pickup module, audio signal separation module, coded treatment module and
Control module is sequentially connected, and the audio signal separation module is connect with control module.
2. the far field speech control system based on television equipment as described in claim 1, which is characterized in that the far field pickup
Module is microphone array, and the microphone array includes diamylose array, four wheat array of bar shaped and annular six wheat arrays.
3. the far field speech control system based on television equipment as claimed in claim 2, which is characterized in that the microphone array
It is classified as digital microphone array.
4. the far field speech control system based on television equipment as claimed in claim 2, which is characterized in that the microphone array
It is classified as simulation microphone array;
The audio signal separation module includes AD conversion unit, and the AD conversion unit and simulation microphone array connect
It connects.
5. the far field speech control system based on television equipment as claimed in claim 2, which is characterized in that the microphone array
Column are set to inside television equipment, are located at television equipment bottom or top middle position.
6. the far field speech control system based on television equipment as described in claim 1, which is characterized in that the control module
It further include standby controllable interface, the standby controllable interface is connect with coded treatment module.
7. such as the far field speech control system as claimed in any one of claims 1 to 6 based on television equipment, which is characterized in that institute
Stating television equipment includes digital television or set-top box.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201820976245.1U CN208724111U (en) | 2018-06-22 | 2018-06-22 | Far field speech control system based on television equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201820976245.1U CN208724111U (en) | 2018-06-22 | 2018-06-22 | Far field speech control system based on television equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN208724111U true CN208724111U (en) | 2019-04-09 |
Family
ID=65971938
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201820976245.1U Active CN208724111U (en) | 2018-06-22 | 2018-06-22 | Far field speech control system based on television equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN208724111U (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110012331A (en) * | 2019-04-11 | 2019-07-12 | 杭州微纳科技股份有限公司 | A kind of far field diamylose far field audio recognition method of infrared triggering |
CN110366067A (en) * | 2019-05-27 | 2019-10-22 | 深圳康佳电子科技有限公司 | A kind of far field voice module echo cancel circuit and device |
CN111128167A (en) * | 2019-12-30 | 2020-05-08 | 深圳创维-Rgb电子有限公司 | Far-field voice awakening method and device, electronic product and storage medium |
-
2018
- 2018-06-22 CN CN201820976245.1U patent/CN208724111U/en active Active
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110012331A (en) * | 2019-04-11 | 2019-07-12 | 杭州微纳科技股份有限公司 | A kind of far field diamylose far field audio recognition method of infrared triggering |
CN110012331B (en) * | 2019-04-11 | 2021-05-25 | 杭州微纳科技股份有限公司 | Infrared-triggered far-field double-microphone far-field speech recognition method |
CN110366067A (en) * | 2019-05-27 | 2019-10-22 | 深圳康佳电子科技有限公司 | A kind of far field voice module echo cancel circuit and device |
CN110366067B (en) * | 2019-05-27 | 2021-07-20 | 深圳康佳电子科技有限公司 | Far field voice module echo cancellation circuit and device |
CN111128167A (en) * | 2019-12-30 | 2020-05-08 | 深圳创维-Rgb电子有限公司 | Far-field voice awakening method and device, electronic product and storage medium |
CN111128167B (en) * | 2019-12-30 | 2023-10-27 | 深圳创维-Rgb电子有限公司 | Far-field voice awakening method and device, electronic product and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107454508B (en) | TV set and TV system of microphone array | |
CN106910500B (en) | Method and device for voice control of device with microphone array | |
WO2018137704A1 (en) | Microphone array-based pick-up method and system | |
CN208724111U (en) | Far field speech control system based on television equipment | |
WO2020103703A1 (en) | Audio data processing method and apparatus, device and storage medium | |
CN111223497A (en) | Nearby wake-up method and device for terminal, computing equipment and storage medium | |
CN107016993A (en) | The voice interactive system and method for a kind of smart home | |
CN105338459A (en) | MEMS (Micro-Electro-Mechanical System) microphone and signal processing method thereof | |
CN102932212A (en) | Intelligent household control system based on multichannel interaction manner | |
CN101996630A (en) | Automatic sound recognition based on binary time frequency unit | |
CN109949808A (en) | The speech recognition appliance control system and method for compatible mandarin and dialect | |
US20170287480A1 (en) | Voice wake-up method and device | |
CN112532266A (en) | Intelligent helmet and voice interaction control method of intelligent helmet | |
CN111383649B (en) | Robot and audio processing method thereof | |
CN110349582A (en) | Display device and far field speech processing circuit | |
CN109412544B (en) | Voice acquisition method and device of intelligent wearable device and related components | |
CN108447483A (en) | Speech recognition system | |
CN208691406U (en) | Far field speech collecting system for smart television | |
CN214226506U (en) | Sound processing circuit, electroacoustic device, and sound processing system | |
CN106328154B (en) | A kind of front audio processing system | |
US9779731B1 (en) | Echo cancellation based on shared reference signals | |
CN115206306A (en) | Voice interaction method, device, equipment and system | |
CN110517702A (en) | The method of signal generation, audio recognition method and device based on artificial intelligence | |
CN106409306A (en) | Intelligent system obtaining human voice and obtaining method based on the system | |
WO2021031811A1 (en) | Method and device for voice enhancement |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant |