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

Underdetermined voice blind source separation method and device

A technology of blind source separation and speech, which is applied in speech analysis, instruments, character and pattern recognition, etc.

Inactive Publication Date: 2019-12-03
SHANGHAI NORMAL UNIVERSITY
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Using this improved two-step method can solve the problem of underdetermined blind source separation under the sparse representation of two different types of speech signals, and is suitable for source signal recovery with more than two observation signal numbers

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
  • Underdetermined voice blind source separation method and device
  • Underdetermined voice blind source separation method and device
  • Underdetermined voice blind source separation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0079] Such as figure 1 As shown, a preferred embodiment of the present invention discloses a method for blind source separation of underdetermined speech comprising the following steps:

[0080] Step 100, obtain the observation signal, process the obtained observation signal, and obtain the sparse feature of the speech source signal; (processing points: stable source signal, use Fourier transform; unstable source signal needs to use short-time Fourier transform Leaf transform) to obtain the sparse features of the speech source signal (shown by the scatter diagram); when obtaining a stable source signal, it is sufficient to perform Fourier transform on the observed signal.

[0081] Among them, the observation signal is the aliasing signal of multiple speech source signals received by the sensor in the space. Taking the observed signal as input, multiple separated speech source signals are obtained through the whole underdetermined blind source separation algorithm.

[0082] ...

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 underdetermined voice blind source separation method, which comprises the following steps of acquiring an observation signal, processing the acquired observation signal, andacquiring a voice source signal sparse characteristic; obtaining aliasing matrix estimation by using an ant colony K-means clustering algorithm according to the obtained sparse features (representedby a scatter diagram) of the voice source signal; and recovering the voice source signal by using a greedy sparsification method according to the estimated aliasing matrix and the processed observation signal. According to the underdetermined voice blind source separation method, the underdetermined blind source separation problem under sparse representation of two different types of voice signalscan be solved by using the improved two-step method, and the underdetermined voice blind source separation method is suitable for source signal recovery of more than two observation signals.

Description

technical field [0001] The invention relates to the field of speech signal processing, in particular to a method and device for blind source separation of underdetermined speech. Background technique [0002] In real life, individuals are often in an environment that contains multiple sound sources such as conversations, music, and other background noises. The human brain can distinguish speech from different sound sources in this complex mixed speech environment. With the development of artificial intelligence speech technology, how to use computer instead of human brain to realize intelligent blind source separation of mixed speech signals has become a research hotspot of scholars in recent years. It is worth noting that in the application of speech signal processing, there are usually many types of sound sources and unknown noises in a certain space, and the number of sensors responsible for receiving speech signals is usually limited, resulting in the number of received ...

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): G10L21/0272G10L21/0308G06K9/62
CPCG10L21/0272G10L21/0308G06F18/23
Inventor 魏爽杨璟安徐朋龙艳花杨春夏张巧珍
Owner SHANGHAI NORMAL UNIVERSITY
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com