Voice signal characteristics extracting method based on tensor decomposition

A speech signal and tensor decomposition technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problem that speech features only contain part of the speech signal information, and achieve the effect of enhancing the representation ability

Inactive Publication Date: 2013-05-22
INNER MONGOLIA UNIV OF SCI & TECH +1
View PDF3 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to fully characterize the speech signal, and propose a speech signal feature extraction method

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 signal characteristics extracting method based on tensor decomposition
  • Voice signal characteristics extracting method based on tensor decomposition
  • Voice signal characteristics extracting method based on tensor decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be described in detail below in conjunction with accompanying drawing and embodiment, also described the technical problem and beneficial effect that the technical solution of the present invention solves simultaneously, it should be pointed out that described embodiment is only intended to facilitate the understanding of the present invention, and It has no limiting effect on it.

[0040] like figure 1 Shown, the speech signal feature extraction method based on tensor decomposition of the present invention specifically comprises the following steps:

[0041] Step 1: The speech signal to be processed is divided into frames using a Hamming window, the frame length is L, and the frame shift is M, so that the speech signal is divided into N frames, and the frame sequence is obtained after sequential arrangement;

[0042] Step 2: Carry out R layer wavelet decomposition respectively to each frame speech signal after framing, because speech signal ...

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 a voice signal characteristics extracting method based on tensor decomposition and belongs to the technical field of voice signal processing. The voice signal characteristics extracting method based on the tensor decomposition comprises the following steps: having multi-layer wavelet decomposition to voice signals after framing, respectively extracting MR frequency cepstrum coefficients, the corresponding first order difference coefficient and second order difference coefficient from a plurality of component information after the wavelet decomposition to form a characteristic parameter vector, establishing a third order voice tensor and having tensor decomposition to the third order voice tensor, and calculating component information order and characteristic projection of characteristic parameters. Marticulated results are characteristics carried by each frame of voice signals. Compare with the traditional characteristic parameters, the voice signal characteristics extracting method based on the tensor decomposition has the advantages of enhancing representational ability to the voice signals, acquiring characteristics which carries more comprehensive voice signals, and improving the effects of voice signal processing systems such as voice identifying signal processing system, speaker identifying signal processing system.

Description

technical field [0001] The invention relates to a speech signal feature extraction method, in particular to a speech signal feature extraction method based on tensor decomposition, which belongs to the technical field of speech signal processing. Background technique [0002] Speech signal is a non-stationary time-varying signal, which carries various information. In speech signal processing such as speech coding, speech synthesis, speech recognition and speech enhancement, it is necessary to extract various information contained in speech. Generally speaking, the purpose of speech processing is to obtain certain speech feature parameters for efficient transmission or storage; or to achieve a certain purpose through certain processing operations, such as identifying the content of the speech, identifying the speaker, Synthetic speech, etc., simply put, is to conveniently and effectively extract and represent the information carried by the speech signal. [0003] With the c...

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): G10L15/02G10L19/032
Inventor 杨立东王晶
Owner INNER MONGOLIA UNIV OF SCI & TECH
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap