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

Method and system for self-adaptive correction of user's personal pronunciation dictionary model

An adaptive, dictionary technology, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as inability to effectively deal with recognition errors, and inability to batch modify wrong pronunciations.

Active Publication Date: 2021-07-06
AISPEECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to at least solve the problem that the existing technology cannot effectively deal with the recognition errors caused by the user's inaccurate pronunciation, and at the same time, the problem that a class of regular wrong pronunciations cannot be modified in batches

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 self-adaptive correction of user's personal pronunciation dictionary model
  • Method and system for self-adaptive correction of user's personal pronunciation dictionary model
  • Method and system for self-adaptive correction of user's personal pronunciation dictionary model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to make the objects, technical solutions, and advantages of the present invention more clearly, the technical solutions in the embodiments of the present invention will be described in contemplation in the embodiments of the present invention, and will be described, and the embodiments described in the embodiments of the present invention will be described. It is a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, those of ordinary skill in the art will belong to the scope of the present invention without all other embodiments obtained without creative labor.

[0029] Such as figure 1 A process diagram of an adaptive correction method of a pronunciation dictionary model provided by an user of the present invention, including the following steps:

[0030] S11: Establish the initial personal pronunciation dictionary model, using the pronunciation dictionary model to identify the user's voi...

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

An embodiment of the present invention provides an adaptive correction method for a user's personal pronunciation dictionary model. The method includes: establishing an initial personal pronunciation dictionary model, receiving a user's correction of an erroneous word in the model recognition result, and comparing the confidence in the acoustic score of the erroneous word with the preset confidence when the correction is a matching replacement word. Determine whether there is a pronunciation problem; determine whether the pronunciation relationship between the wrong word and the replacement word belongs to the regular fuzzy sound rule, compare the number of historical corrections, and if it belongs, adjust the pronunciation weight of the same pronunciation as the wrong pronunciation in batches. If it does not belong, adjust it separately Mispronunciation weights, based on the adjusted weights, adaptively correct the individual pronunciation dictionary model. The embodiment of the present invention also provides a system for self-adaptive modification of the user's personal pronunciation dictionary model. The embodiment of the present invention effectively handles recognition errors caused by inaccurate pronunciations of users, and batch corrections can be performed on a class of regular wrong pronunciations.

Description

Technical field [0001] The present invention relates to the field of speech recognition, and more particularly to an adaptive correction method and system of a pronunciation dictionary model of a user. Background technique [0002] In order to make speech recognition more user-friendly, in speech recognition, in addition to using the shared language model, the individual language model for each user is added. This personal language model can be based on the user's past input, or the model obtained by the user-defined word table, in the actual speech recognition, the score of the language model is usually interpolated by the shared language model and the individual's language model. . [0003] In implementing the present invention, the inventors have discovered at least the following problems in the relevant techniques: [0004] This technique is valid based on the ASR (Automatic Speech Recognition, Automatic Speech Recognition) system based on the user's personal language model, ...

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): G10L15/07G10L15/06G10L15/187
CPCG10L15/063G10L15/07G10L15/187G10L2015/0635G10L2015/0636G10L2015/0638
Inventor 陈梦姣
Owner AISPEECH 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