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

Method for extracting mixed characteristic parameters of voice signals

A speech signal and mixed feature technology, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as poor robustness, insufficient characterization ability, and single parameters

Inactive Publication Date: 2015-09-09
INST OF INFORMATION TECH OF GUET
View PDF1 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention aims to solve the problem of low recognition rate and poor robustness existing in the prior art
[0005] In order to solve the problems of single speech feature parameters, insufficient characterization ability, and poor robustness, the present invention proposes a method for extracting speech signal mixing feature parameters. Extraction can improve the recognition rate without increasing the amount of calculation, and improve the robustness and robustness of the system

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 for extracting mixed characteristic parameters of voice signals
  • Method for extracting mixed characteristic parameters of voice signals
  • Method for extracting mixed characteristic parameters of voice signals

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In order to understand the above-mentioned purpose, features and advantages of the present invention more clearly, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0046] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways than described here. Therefore, the protection scope of the present invention is not limited by the specific implementation disclosed below. Example limitations.

[0047] Refer below Figure 1-10 The method for extracting parameters of speech signal mixing features according to the embodiment of the present invention will be further described.

[0048] Such as figure...

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 provides method, based on Fisher criteria and k-means cluster, for extracting mixed characteristic parameters of voice signals. The method includes a process for pretreating voice signals x(n), a characteristics extraction process and a characteristics mixing process, and is characterized in that the process for pretreating voice signals x(n) includes preemphasizing, enframing and windowing of the voice signals x(n) and end points detection and processing, the characteristics extraction process includes an LPCC parameter extraction process, an MFCC parameter extraction process and a LPCC differential parameter and MFCC difference extraction process, and the characteristics mixing process includes mixing the LPCC parameter, the MFCC parameter and the differential parameters according to Fisher criteria and k-means. The method improves recognition rate without increasing calculating time, and the robustness and stability of a system are improved.

Description

technical field [0001] The invention relates to the field of speech signal processing, in particular to a method for extracting speech signal mixing characteristic parameters Background technique [0002] Speech signal is a very complex non-stationary signal, which contains rich characteristic information of individuals and speech itself, and the extraction of its characteristic parameters is very important to the effect of speech recognition. Feature parameter extraction refers to finding the intrinsic feature parameters for different speech segments. Usually, the feature parameters can be roughly divided into three categories: the first category is time-domain parameters, such as short-term average energy, formant, short-term average amplitude, short-term Average zero-crossing rate, short-term autocorrelation function, high-order statistics and pitch period, etc.; the second category is frequency domain parameters, such as linear predictive coefficient (LPC), linear predic...

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): G10L15/02G10L15/08
Inventor 景新幸
Owner INST OF INFORMATION TECH OF GUET
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