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

Continuous speech recognition method and system

A technology of speech recognition and speech, applied in speech recognition, speech analysis, instruments, etc., to achieve the effect of improving accuracy, avoiding transformation, and solving noise robustness problems

Active Publication Date: 2020-02-07
IFLYTEK CO LTD +1
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a continuous speech recognition method and system to solve the noise robustness problem in the existing speech recognition based on DNN denoising and improve the correctness of continuous speech recognition

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
  • Continuous speech recognition method and system
  • Continuous speech recognition method and system
  • Continuous speech recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0077] In the continuous speech recognition method and system of the embodiments of the present invention, a neural network that integrates speech denoising and acoustic classification is trained in advance, and then the continuous speech signal is decoded based on the neural network to obtain a speech recognition result.

[0078] The above-mentioned neural network that combines speech denoising and acoustic classification is obtained by splicing and merging th...

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 continuous speech recognition method and a continuous speech recognition system. The method comprises the steps of pre-training a neural network integrating speech de-noising and acoustic classification, receiving a continuous speech signal to be identified, extracting the acoustic characteristics of the speech signal, getting the posteriori probability of a speech modeling unit according to the acoustic characteristics and the neural network, and performing viterbi decoding on the posteriori probability of the modeling unit of all frames of speech in a continuous speech segment of the speech signal to get a speech recognition result. By using the method and the system, the accuracy of the continuous speech recognition result is improved.

Description

technical field [0001] The invention relates to the field of speech signal processing, in particular to a continuous speech recognition method and system. Background technique [0002] It has become an urgent need for the application and development of information technology to realize humanized and intelligent effective interaction between man and machine, and to build an efficient and natural human-machine communication environment. As the most convenient and quick way for people to communicate with the outside world, speech recognition technology has always been a hot spot for researchers in related fields. [0003] In the traditional speech recognition system, the speech signal to be recognized is denoised by using noise reduction methods such as microphone arrays, filters, and spectral subtraction, and then the features of the denoised speech signal are extracted, and the follow-up is performed based on the pre-trained acoustic model. identification work. The effect o...

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 Patents(China)
IPC IPC(8): G10L15/20G10L15/02G10L15/06G10L15/16
Inventor 杜俊高天戴礼荣胡国平胡郁刘庆峰
Owner IFLYTEK 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