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

Voice information recognition method and terminal equipment

A technology for voice information and terminal equipment, which is applied in the field of information recognition and can solve the problems of unstable sound source and deviation of characteristic information.

Active Publication Date: 2014-07-23
HISENSE
View PDF3 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a method for voice information recognition, which is used to solve the problem in the prior art that when the sound source of the voice information to be recognized is unstable or the sound transmission equipment interferes, the determined characteristic information is prone to deviation.

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
  • Voice information recognition method and terminal equipment
  • Voice information recognition method and terminal equipment
  • Voice information recognition method and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0082] The embodiment of the present invention provides a voice information recognition method and a terminal device, which extract voiced sound information from the voice information to be recognized, extract pitch frequency parameters and MFCC from the voiced sound information, and process the pitch frequency parameters to obtain pitch frequency parameter matching values; The MFCC is processed to obtain the MFCC parameter matching value; the characteristic information of the speech information to be recognized is determined according to the pitch frequency parameter matching value and the MFCC parameter matching value.

[0083] Human speech can be roughly divided into two parts: unvoiced and voiced. The voiced segment is characterized by a relatively high energy distribution, has the periodicity of the voice fundamental tone, has a formant structure in the frequency domain, and most of the energy is concentrated in the low frequency band. Inside. The amplitude of unvoiced so...

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 the field of information recognition, in particular to a voice information recognition method and terminal equipment. The voice information recognition method and the terminal equipment resolve the problem in the prior art that when a sound source of voice information to be recognized is not stable or sound transmission equipment generates interference, determined feature information has deviation easily. Voiced sound information is extracted from the voice information to be recognized, fundamental tone frequency parameters and an MFCC are extracted from the voiced sound information, the fundamental tone frequency parameters are processed to obtain a fundamental tone frequency parameter matching value, the MFCC is processed to obtain an MFCC parameter matching value, and the feature information of the voice information to be recognized is determined according to the fundamental tone frequency parameter matching value and the MFCC parameter matching value. Due to the facts that voiced sound in the voice information has the periodicity of a voice fundamental tone, the voiced sound information has a relatively fixed frequency in general, the characteristic of the voiced sound information can be treated as a quasi-steady-state process, and the probability that the feature information of the voice information determined according to the voiced sound information has mistakes is low.

Description

technical field [0001] The invention relates to the field of information recognition, in particular to a voice information recognition method and terminal equipment. Background technique [0002] With the development of electronic technology, electronic equipment has been upgraded to have more and more functions. Among them, the voice control function has attracted much attention, and various voice assistant applications have emerged. Voice assistant applications enable users to use electronic equipment Read text messages, introduce restaurants, ask about the weather, recommend programs, etc. The key to realizing voice assistant applications is the speech recognition system. The speech signal not only contains the semantic information of the speaker, but also contains the characteristic information of the speaker. People can extract the speaker's gender and other identity information from the speech signals of different speakers. . [0003] The current speech information r...

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): G10L15/02G10L15/07G10L15/08
Inventor 匡涛贾魁王勇进任晓楠
Owner HISENSE
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