Method and device for continuous speech recognition result evaluation

A speech recognition and result evaluation technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as errors, false deletions, and inaccurate evaluations, and achieve the effects of reducing false errors, improving correctness, and ensuring priority

Inactive Publication Date: 2009-12-23
BEIJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The existing technology is inaccurate in evaluating the results of word-based continuous speech recognition, resulting in many false errors, especially false deletion, substitution, and insertion errors

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
  • Method and device for continuous speech recognition result evaluation
  • Method and device for continuous speech recognition result evaluation
  • Method and device for continuous speech recognition result evaluation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] 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 creative efforts fall within the protection scope of the present invention.

[0028] Such as figure 1 Shown is the device block diagram of the embodiment of the present invention, including:

[0029] Input unit 101, input speech recognition result sequence (T sequence) and reference sequence (R sequence), save and as the data source of follow-up processing unit, the sequence of input is word sequence, adopts separator (as space, return between words) car line break, tab, etc.), with a special character (such as ".") as the end symbol;

[0...

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 embodiment of the invention discloses a continuous speech recognition result evaluation method based on character and word mixing, and the method comprises the steps of generating an R-T matching plane with character and word mixing according to an input speech recognition result sequence and a reference sequence; carrying out matching in the R-T plane according to a DP algorithm, wherein, local matching paths adopt a plurality of matching paths based on the character and word mixing and adopt a variety of path scoring functions; and carrying out path backtracking, thereby obtaining the best matching result and doing statistics of speech recognition performance-related information. The invention further discloses a continuous speech recognition result evaluation device based on the character and word mixing, and the utilization of the embodiment of the invention can effectively reduce false errors in the recognition result evaluation and effectively improve the word-based continuous speech recognition result evaluation precision.

Description

technical field [0001] The invention relates to the field of speech recognition, in particular to a method and device for evaluating continuous speech recognition results. Background technique [0002] The result evaluation of continuous speech recognition usually adopts the method of dynamic programming to obtain the best matching result, and the HResults tool in Hidden Markov ToolKit (HTK) is a typical representative for completing this task. [0003] When performing a match, the matching unit can be a word, or a character, a phoneme, etc., and only matching at the same level can be completed, that is, word-word matching or word-word matching. In Chinese continuous speech recognition, words or syllables are usually used as matching primitives, and phoneme-based matching is usually used when only the performance of the acoustic model needs to be evaluated. Word-based matching is rarely used because it produces some false matches. [0004] In word-based result matching, th...

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): G10L15/00G10L25/51
Inventor 刘刚陈伟郭军国玉晶
Owner BEIJING UNIV OF POSTS & TELECOMM
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