Microphone-array-based speech recognition system and method

A microphone array and speech recognition technology, applied in the field of speech recognition system, can solve the problems of mismatch between test environment and training environment, information without considering noise, etc.

Active Publication Date: 2013-01-30
IND TECH RES INST
View PDF4 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The corpus required for the speech model 110 training needs to be re-recorded and filtered, and the noise information is not considered, so the settings of the test environment and the training environment may not match

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
  • Microphone-array-based speech recognition system and method
  • Microphone-array-based speech recognition system and method
  • Microphone-array-based speech recognition system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] In an implementation example of the microphone array-based speech recognition system and method of the present disclosure, the noise mask ( noise masking) to suppress the part of the spectrum that is disturbed by noise in the speech feature vector, so as to improve the speech recognition rate. The embodiments of the present disclosure aim at adjusting the parameters of the noise mask in environments with different noises (such as driving), so as to adapt to the voice application in the actual environment. The embodiment of the present disclosure combines noise masking and speech recognition into one, and uses the existing speech model without re-recording the corpus or training the speech model, providing better human-computer interaction with speech in a noisy environment Voice interface and user experience.

[0045] In the embodiment of the present disclosure, using at least one speech model Λ SP with at least one filled model Λ F , and calculate the confidence val...

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

Disclosed is a microphone-array-based speech recognition system and method. The speech recognition system combines a noise cancelling technique for cancelling noise of input speech signals from an array of microphones, according to at least an inputted threshold. The system receives noise-cancelled speech signals outputted by a noise masking module through at least a speech model and at least a filler model, then computes a confidence measure score with the at least a speech model and the at least a filler model for each threshold and each noise-cancelled speech signal, and adjusts the threshold to continue the noise cancelling for achieving a maximum confidence measure score, thereby outputting a speech recognition result related to the maximum confidence measure score.

Description

technical field [0001] The present disclosure relates to a Microphone-Array-Based speech recognition system and method. Background technique [0002] In recent years, the number of users of mobile devices such as tablet computers and mobile phones has increased significantly, and automotive electronics and robots have also developed rapidly. It can be seen from these fields that the demand for voice applications in the future will grow rapidly. Google's Nexus One and Motorola's Droid brought Active Noise Cancellation (ANC) technology to the mobile phone market, improving the input end of voice applications, and making the back-end voice recognition or its applications perform better, so that users can Get a better experience. In recent years, mobile phone manufacturers have also actively conducted research on noise cancellation technology for mobile phones. [0003] There are two types of common Robust speech recognition technologies. One is the two-stage robust speech r...

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): G10L15/20G10L21/02H04R3/00
CPCH04R3/005G10L21/02H04R1/406G10L21/0208G10L15/142G10L2021/02166H04R3/00G10L15/20
Inventor 廖宪正
Owner IND TECH RES INST
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