Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

HMM model-based dialect recognition method, device, equipment and medium

A dialect and model technology, applied in the field of dialect recognition based on the HMM model, can solve problems such as inability to accurately reflect the pronunciation characteristics of dialects, achieve the effect of improving the recognition rate and realizing system performance

Inactive Publication Date: 2019-07-02
CHINA MOBILE GROUP ANHUI +1
View PDF8 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Second, the built model cannot accurately reflect the pronunciation characteristics of dialects.

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
  • HMM model-based dialect recognition method, device, equipment and medium
  • HMM model-based dialect recognition method, device, equipment and medium
  • HMM model-based dialect recognition method, device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0097] An embodiment of the present invention provides a method for recognizing dialects such as Huizhou dialect based on an HMM model. figure 1 is a flow chart of the HMM model-based dialect recognition method according to an embodiment of the present invention. Such as figure 1 As shown, the steps of the identification method include:

[0098] Step S103, obtaining the acoustic feature sequence of the dialect speech to be recognized using the Viterbi algorithm;

[0099]Step S104, input the acoustic feature sequence into the HMM model library and compare it with the HMM model of the word, and identify the dialect in batches and / or in real time.

[0100] Through the steps of the embodiments of the present invention, it is possible to solve the problem in the related art that it is difficult to identify sub-dialects within the dialect family, and realize accurate and rapid speech recognition of dialects.

[0101] figure 2 It is an optional flow chart of the HMM model-based ...

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 an HMM model-based dialect recognition method, a dialect recognition device, equipment and a medium. The method comprises the following steps: acquiring an acoustic feature sequence of to-be-recognized dialect voices processed by utilizing a Viterbi algorithm; inputting the acoustic feature sequence into an HMM model library, comparing the acoustic feature sequence with anHMM model of words, and identifying dialects in batches and / or in real time. According to the technical scheme of the embodiment of the invention, the voice recognition of dialects such as Huizhou dialects and the like can be realized. The voice recognition rate of dialects is improved.

Description

technical field [0001] The present invention relates to the technical field of speech recognition, in particular to a dialect recognition method, device, equipment and medium based on an HMM model. Background technique [0002] The research on speech recognition has achieved many results, but it still faces many challenges, the biggest challenge is the dialect problem. The incompatibility of dialects in various parts of China makes the accents of people in different regions quite different. This difference has caused great difficulties to the speech recognition system and limited its application and development. [0003] As the carrier of other intangible cultural heritage, dialect itself is also a kind of intangible cultural heritage. As an important tool for people to communicate, dialect carries a large amount of cultural information accumulated by a specific ethnic group in the long-term historical development. irreplaceable role. However, nowadays, the use of dialects...

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): G10L15/06G10L17/04G10L17/08G10L17/16G10L25/51
CPCG10L15/06G10L17/04G10L17/08G10L17/16G10L25/51
Inventor 童芳
Owner CHINA MOBILE GROUP ANHUI
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
Eureka Blog
Learn More
PatSnap group products