Rapid decoding method for voice identifying system

A technology of speech recognition and decoding methods, applied in speech recognition, speech analysis, instruments, etc., which can solve the problems of high hardware computing power and memory requirements

Inactive Publication Date: 2003-11-12
INST OF ACOUSTICS CHINESE ACAD OF SCI +1
View PDF0 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0020] The purpose of the present invention is to provide a kind of fast decoding operation method in the continuous speech recognition system of improving current non-specific NPC vocabulary, and this method further solves current embedded speech recognition technology,

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
  • Rapid decoding method for voice identifying system
  • Rapid decoding method for voice identifying system
  • Rapid decoding method for voice identifying system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0084] specific implementation

[0085] image 3 The decoding operation flow chart of the present invention is given. Depend on figure 2 , combine image 3 , the operating flow of the voice recognition system based on the decoding operation subsystem of the present invention is: the input voice analog signal is converted into a digital signal; the digital signal is processed in frames, and the characteristic parameters of each frame of voice are extracted, and each voice Frame corresponds to a feature vector, obtains the feature vector sequence of input speech; Utilizes feature code book to carry out quantization encoding to described feature vector sequence, each speech frame corresponds to a feature codeword vector, obtains corresponding feature codeword vector sequence; Speech The speech frame filtering unit of the characteristic codeword vector sequence input decoding operation subsystem, do the speech frame filtering operation, remove the characteristic codeword vecto...

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

(1) Initializing the decoding arithmetic elements. (2) The feature code word vectors of next voice frame are taken out from the voice feature code word sequence with length T in the input decoding arithmetic element. The current voice frame is Ot, 1<=t<=T. (3) Filtering the current voice frame Ot. (4) Based on Ot, each active node of the token resource L t[I] in each layer I of token resource L t of lexicographic tree at t time is judged. (5) Processing the token between nods of lexicographic tree. (6) Based on the maximum probability of partial directory path, the self-adapting adjustment is carried out for the threshold related to the lopping of branches. (7) Repeating steps (2)-(6). The generated best text string matched to the acoustic model and the language model is output. Thus, the result of the voice recognition is generated. Comparing with traditional methods, the strategy speeds up decoding operation.

Description

technical field [0001] The invention relates to a fast decoding method in a speech recognition system. Background technique [0002] The decoding operation is the main component of the speech recognition system. Its function is: under the given acoustic model and language model, for the input acoustic observation feature vector sequence, let the computer automatically find out in the search space constructed statically or dynamically. The text string that has the best match with the acoustic model and the language model to convert the user's speech input into the corresponding text. [0003] figure 1 Shown is a structural block diagram of a known speech recognition system, the analog speech is transformed into a computer-processable digital signal through the analog-to-digital conversion unit 11, and then the digital signal is processed by using the feature extraction unit 12 in frames, usually the frame length is 20ms, the frame shift is 10ms, extract the MFCC parameters ...

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
IPC IPC(8): G10L15/065
Inventor 韩疆颜永红潘接林张建平
Owner INST OF ACOUSTICS CHINESE ACAD OF SCI
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