Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and system for the post-treatment of a voice recognition result

A speech recognition and processing device technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of unreliable post-processing methods and wrong post-processing solutions, etc., and achieve the effect of easy implementation and simple implementation steps

Inactive Publication Date: 2018-03-02
ZETES IND SA
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The inventors have thus found that, in some cases, this approach can lead to wrong post-processing solutions, i.e., solutions that do not match the information actually provided by the speaker
Therefore, this postprocessing method is not reliable enough

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 system for the post-treatment of a voice recognition result
  • Method and system for the post-treatment of a voice recognition result
  • Method and system for the post-treatment of a voice recognition result

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0092] figure 1 A speaker 40 (user 40 ) is shown speaking information 50 into a microphone 5 . This information 50 is then passed to a speech recognition engine 10 known to those skilled in the art. There are various models and various brands on the market. Typically, the microphone 5 forms part of the speech recognition engine 10 . The speech recognition engine processes the information 50, for example using a Hidden Markov Model (HMM) based speech recognition algorithm. This results in a speech recognition result of 100. An example of results 100 are hypotheses generated by speech recognition engine 10 . Another example of result 100 is a solution obtained from a speech recognition algorithm and post-processing operations applied to one or more hypotheses generated, for example, by speech recognition engine 10 . A post-processing module for providing such a solution may form part of the speech recognition engine 10 . Results 100 are typically in the form of text, which...

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 relates to a method for the post-treatment of a voice recognition result (100), said result (100) comprising a beginning (111), an end (112) and a plurality of elements (113), said method comprising the following steps: reading said result (100); selecting one of the elements (113) thereof; determining whether it is valid; repeating the steps of selecting the element (113) and determining the validity thereof or not; and if at least one element (113) has been determined as being valid, determining a post-treated solution (200) by reusing at least one such valid element (113). Themethod of the invention is characterised in that said element (113) is selected from said end (112) to said beginning (111) of the result (100) in a consecutive manner.

Description

technical field [0001] According to a first aspect, the invention relates to a method of post-processing speech recognition results. According to a second aspect, the present invention relates to a system (or device) for post-processing speech recognition results. According to a third aspect, the invention relates to a program. According to a fourth aspect, the invention relates to a storage medium (eg USB memory stick, CD-ROM or DVD disc) comprising instructions. Background technique [0002] Speech recognition engines allow results to be generated from speech or audio information, usually in the form of text or code that can be processed by machines. This technique is widely used at present and is considered to be very useful in document US 6754629 B1 which teaches in particular various applications of speech recognition. [0003] Research continues to improve the results provided by speech recognition engines. For example, the public document US2014 / 0278418A1 proposes...

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): G10L15/22
CPCG10L15/22G10L15/26G10L15/142G10L15/19
Inventor 琼-吕克·福斯特
Owner ZETES IND SA