Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Loudspeaker noise filtering device and method in speech recognition

A technology of speech recognition and filtering device, which is applied in speech recognition, sounding equipment, speech analysis, etc., can solve the problems such as the decline of recognition efficiency, and achieve the effects of improving clarity, improving accuracy, and eliminating background noise.

Inactive Publication Date: 2016-11-09
HUIZHOU TCL MOBILE COMM CO LTD
View PDF7 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But there is a situation, that is, when the terminal is playing music, the user speaks into the microphone, and the music from the speaker will be brought in, resulting in a significant drop in recognition efficiency.

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
  • Loudspeaker noise filtering device and method in speech recognition
  • Loudspeaker noise filtering device and method in speech recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In view of the disadvantages of high noise and reduced recognition accuracy in the prior art when users perform speech recognition while playing music, the purpose of the present invention is to provide a device and method for filtering speaker noise in speech recognition, which can generate and output from the speaker. The reverse audio signal with the opposite waveform of the first audio signal eliminates the background noise output by the mobile terminal itself, greatly improves the clarity of the voice signal input by the user during voice recognition, and further improves the accuracy of voice recognition.

[0038] In order to make the object, technical solution and effect of the present invention more clear and definite, the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to li...

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 a loudspeaker noise filtering device and method in speech recognition, wherein the loudspeaker noise filtering device comprises an audio frequency output module, a loudspeaker, a processing module and a microphone; the loudspeaker noise filtering method comprises: outputting a first audio frequency signal selected by a user to the loudspeaker through the audio frequency output module; the loudspeaker playing the first audio frequency signal; the processing module generating a reverse audio frequency signal according to the first audio frequency signal; and the microphone receiving the first audio frequency signal, the reverse audio frequency signal and the voice signal inputted by the user, performing synthesis treatment, and outputting the voice signal to be recognized to a voice database. The method generates the reverse audio frequency signal having waveforms opposite to the first audio signal frequency outputted by the loudspeaker so as to remove the background noise outputted by a mobile terminal, substantially improves the sharpness of the voice signal inputted by a user in speech recognition, and furthermore increases speech recognition accuracy.

Description

technical field [0001] The invention relates to the technical field of speech recognition, in particular to a device and method for filtering loudspeaker noise in speech recognition. Background technique [0002] Speech recognition technology is gradually becoming the key technology of human-machine interface in information technology. The combination of speech recognition technology and speech synthesis technology enables people to get rid of the keyboard and operate through voice commands. The rise of the mobile Internet is becoming the most important application environment for voice recognition, such as Apple's Siri, domestic Xunfei software, etc., which can efficiently recognize the user's voice. [0003] At present, similar software can be installed on almost all smart terminals, which can convert the user's voice into text, match the voice with the background database, generate text display, and even directly control it. In order to recognize speech efficiently, it i...

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): G10K11/178G10L15/22H04R3/00
CPCG10K11/178G10L15/22H04R3/00
Inventor 齐东京方国宽
Owner HUIZHOU TCL MOBILE COMM CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com