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

Method and apparatus for training English voice model based on Chinese voice information

A voice information and voice model technology, applied in voice analysis, voice recognition, instruments, etc., can solve problems such as scale control of difficult English words, and achieve the effect of improving user experience and controlling scale

Active Publication Date: 2014-03-12
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The problem with the existing technology is that training the English speech model in this way requires a certain scale of English speech data, and it is difficult to control the scale of English words added to the model

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 apparatus for training English voice model based on Chinese voice information
  • Method and apparatus for training English voice model based on Chinese voice information
  • Method and apparatus for training English voice model based on Chinese voice information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0023] figure 1 A schematic diagram of a device for training an English speech model based on Chinese speech information according to one aspect of the present invention is shown. The model training device 1 includes a speech acquisition device 101 , an English judgment device 102 , a speech recognition device 103 and a model training device 104 .

[0024] Wherein, the voice acquisition device 101 acquires the voice data input by the user through the voice acquisition device. Specifically, the user or a large number of users input voice data through interaction with the voice collection device, and the voice acquisition device 101 obtains the voice data input by the user or a large number of users by calling the application program interface (API) provided by the voice collection device. or, the user or a large number of users have input the voice data by i...

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 aims to provide a method and apparatus for training an English voice model based on Chinese voice information. Included are the steps of obtaining voice data inputted by a user through a voice collecting device; determining whether the voice data are English voice data; if so, conducting voice recognition processing for the English voice data based on the Chinese voice information to obtain corresponding pronunciation information to the English voice data; and determining corresponding English data to the English voice data based on the pronunciation information to create or update the English voice model. Compared with the prior art, on the basis of an original Chinese acoustic model, the method and apparatus for training the English voice model based on the Chinese voice information use the similar Chinese voice information and conduct voice recognition processing for the English voice data to obtain the corresponding pronunciation information to the English voice data, thereby achieving the creation or update of the English voice model and effectively controlling the size of the English voice model.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a technique for training an English speech model based on Chinese speech information. Background technique [0002] The existing English speech model training methods generally use the existing English speech database, including speech data and its annotations, add English pronunciation units to the pronunciation unit set, and use English data for training. The problem with the prior art is that training the English speech model in this way requires a certain scale of English speech data, and it is difficult to control the scale of English words added to the model. [0003] Therefore, how to overcome the above difficulties and realize the training of the English speech model while controlling the scale has become one of the problems urgently needed to be solved by those skilled in the art. Contents of the invention [0004] The object of the present inventi...

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): G10L15/06G10L15/00
Inventor 苏丹万广鲁
Owner BEIJING BAIDU NETCOM SCI & TECH 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