Intelligent television voice control recognition system and a recognition method thereof

A recognition system, smart TV technology, applied in the field of intelligent interaction, can solve the problems affecting the accuracy of speech recognition, interference, etc., to achieve the effect of reducing algorithm operation and response speed, design security, and reducing resource consumption

Inactive Publication Date: 2019-01-04
深圳北极鸥半导体有限公司
View PDF11 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the face of voice recognition in the TV scene, there are still sound interferences such as music played by the speaker and people chatting next to them that cannot be eliminated, which will affect the accuracy of voice recognition of people who really need to control the operation of the TV

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent television voice control recognition system and a recognition method thereof
  • Intelligent television voice control recognition system and a recognition method thereof
  • Intelligent television voice control recognition system and a recognition method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Embodiment one, such as figure 1 , figure 2 with image 3 As shown, a smart TV voice recognition system includes a power amplifier module 1, 4 microphones, an 8-way I2S audio input bus 2, a power amplifier sound filter module 3, an audio decoder 5, a voice recognition module 6 and an instruction control module 7. The power amplifier module 1 is a power amplifier speaker of a TV set. The microphones can be MEMS microphones, and here the four microphones are respectively MIC1, MIC2, MIC3, and MIC4. The four microphones are installed side by side and equidistant in a box body 8, and face the front area of ​​the TV.

[0054] In the voice control scenario of the TV, it is often faced with the voice control of a long row of people on the sofa. The source of the voice transmission source used for control is relatively wide, while the sound receiving surface of a single microphone is relatively short and narrow, exceeding After a certain range, the sound intensity of the ra...

Embodiment 2

[0095] Embodiment two, such as Figure 4 As shown, a smart TV voice control recognition system differs from Embodiment 1 in that the system also includes a background sound filter module 4, and the background sound filter module 4 is coupled to the power amplifier sound filter module 3 and the audio decoder 5 Between, after the power amplifier sound signal in the ambient sound signal is eliminated by the power amplifier sound filter module 3, the background sound filter module 4 then filters the background sound in the ambient sound signal to obtain a voice signal, and then transmits the voice signal to the audio decoding Decode at device 5.

[0096] The specific working principle of background sound filtering module 4 filtering background sound is:

[0097] Such as Figure 4 with Figure 5 As shown, the background sound filtering module 4 first establishes a coordinate space corresponding to the actual space, and defines an area close to the front of the TV as the control ...

Embodiment 3

[0110] Embodiment three, such as Figure 4 As shown, a voice-activated recognition system for a smart TV is different from Embodiment 2 in that there is a difference in the way of locating the sound source. Instead of using the direct positioning of the sound, the camera 9 is directly used to determine whether there is a person in the control area 12 to eliminate interference.

[0111] The actual working method is: the instruction control module 7 in the system monitors the voice recognition module 6 and the face recognition module 11 synchronously. Only when the face recognition module 11 recognizes that there is a person in the control area 12 , the command control module 7 executes the command recognized by the voice recognition module 6 .

[0112] In the actual family living environment, the voice of the person chatting on the side will also be collected into the microphone, which will easily cause misrecognition of voice commands. Go to the screen in front of the TV, es...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an intelligent television voice control recognition system and an recognition method thereof, The system comprises a power amplifier module, four microphones, a power amplifiersound filter module, an audio decoder, a speech recognition module and an instruction control module. Four microphones are arranged in lateral parallel, and the ambient sound signals outputted from the microphones and the power amplifier sound signals outputted from the power amplifier module are input to the power amplifier sound filter module. The power amplifier sound signal is used as a reference signal, and the power amplifier sound signal is eliminated by a power amplifier sound filter module, and is decoded by an audio decoder, and then the speech recognition module recognizes the power amplifier sound signal, and sends the recognized instruction to a command control module, and the television is controlled to operate by the command control module. The invention has the advantagesof high speech recognition accuracy, strong anti-interference ability, fast speech recognition speed and rich functions.

Description

technical field [0001] The present invention relates to the technical field of intelligent interaction, more specifically, it relates to a smart TV voice control recognition system and a recognition method thereof. Background technique [0002] Talking to a machine so it can understand what you say has been a long-held dream. The image of the China Internet of Things School-Enterprise Alliance compares speech recognition to "the auditory system of a machine". Speech recognition technology is a high technology that allows machines to convert voice signals into corresponding text or commands through the process of recognition and understanding. Speech recognition technology mainly includes three aspects: feature extraction technology, pattern matching criteria and model training technology. In the field of television, it also has a long history of interactive technology development. From the initial panel control to the later remote control remote control, with the developm...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G10L15/22G10L21/0216H04N21/422H04N21/4223
CPCG10L15/22G10L21/0216G10L2015/223G10L2021/02166H04N21/42203H04N21/4223
Inventor 张思芳刘屹
Owner 深圳北极鸥半导体有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap