Speech recognition decoding method and speech recognition decoding device

A speech recognition and decoding method technology, which is applied in the field of speech recognition and decoding, can solve the problems of consumption, large computing and memory resources, etc., and achieve the effects of accurate acoustic modeling, efficient model representation, and reduced consumption of computing and memory resources

Inactive Publication Date: 2016-08-24
AISPEECH CO LTD +1
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The weighted finite state machine under this fra

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
  • Speech recognition decoding method and speech recognition decoding device
  • Speech recognition decoding method and speech recognition decoding device
  • Speech recognition decoding method and speech recognition decoding device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0033] Fig. 1 shows the flow of a speech recognition decoding method provided by the first embodiment of the present invention, which specifically includes:

[0034] S101 receives voice information, and extracts acoustic features;

[0035] Feature extraction uses traditional signal processing techniques to extract the acoustic information of sound waves frame by frame into a vector for back-end modeling and decoding as input features.

[0036] S102 Calculate the information of the acoustic feature according to the connection time series classification model;

[0037] Wherein, the information of the acoustic feature mainly includes a vector extracted frame by frame from the acoustic information of the sound wave.

[0038] The acoustic...

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 speech recognition decoding method and a speech recognition decoding device, which belong to the field of speech processing. The method comprises steps: speech information is received, and acoustic features are extracted; information of the acoustic features is calculated according to a continuous time sequence classification model; if a frame in the acoustic feature information is a non null model frame, a weighted finite state transducer adaptive to acoustic modeling information is used for linguistic information search and historical data are stored, or otherwise, the frame is discarded. Through building the continuous time sequence classification model, the acoustic modeling is more accurate; through using the weighted finite state transducer, model representation is more efficient, and nearly 50% of computation and memory resource consumption is reduced; and by using a phoneme synchronization method in the case of decoding, the calculation quantity and the times for model search are effectively reduced.

Description

technical field [0001] The invention belongs to the field of speech processing, and in particular relates to a method and device for speech recognition and decoding. Background technique [0002] Speech recognition is an artificial intelligence technology that allows machines to convert speech signals into corresponding text or commands through the process of recognition and understanding. In traditional speech recognition, all linguistic information (including the pronunciation sequence of words, the occurrence probability of word combinations, etc.) structure, and all the converted linguistic information is combined (composition), and after the network structure is globally optimized, an overall speech recognition search network is formed for the decoding process to search in the network. The construction process is roughly shown in the figure (the " / " in the example indicates the path weight): [0003] Traditional speech recognition technology is based on hidden markov ...

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): G10L15/02G10L15/06G10L15/08G10L15/193G10L19/008
CPCG10L15/02G10L15/06G10L15/08G10L15/193G10L19/008G10L2015/025G10L2015/0631G10L15/187G10L19/00
Inventor 俞凯周伟达陈哲怀邓威徐涛
Owner AISPEECH CO LTD
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