Voice underdetermined blind identification method and device based on frequency spectrum correction and data density clustering

A spectrum correction, data density technology, applied in speech analysis, character and pattern recognition, instruments, etc., can solve the problem that the algorithm cannot achieve both high accuracy and high efficiency.

Active Publication Date: 2016-06-08
TIANJIN UNIV
View PDF6 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] From the above analysis, it can be seen that the existing

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 underdetermined blind identification method and device based on frequency spectrum correction and data density clustering
  • Voice underdetermined blind identification method and device based on frequency spectrum correction and data density clustering
  • Voice underdetermined blind identification method and device based on frequency spectrum correction and data density clustering

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0128] Example 1: Consider a signal with three harmonic components g(t)=cos(2πf 1 t)+cos(2πf 2 t)+cos(2πf 3 t), where f 1 =152Hz, f 2 =2f 1 =304Hz, f 3 =3f 1 =456Hz, t is the time independent variable. Suppose the sampling frequency is f s = 16000Hz, the Fourier transform of L=512 points can be used to obtain the frequency spectrum |G(k)|, then the frequency resolution Δf=f s / L=31.25Hz. By the frequency offset formula

[0129] δ=f / Δf-[f / Δf],(14)

[0130] δ can be obtained1 =-0.1360, δ 2 =2δ 1 =-0.2720, δ 3 =3δ 1 =-0.4080, where [·] represents the rounding operation. Its spectrum see figure 1 .

[0131] from figure 1 It can be seen that the ideal spectral line (indicated by the dotted line in the figure) evolves into a cluster of adjacent spectral lines (indicated by the black solid line in the figure). As shown in the figure, the greater the frequency offset, the greater the deviation of the spectral peak from the ideal spectral line, and the more serious t...

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 belongs to the technical field of digital signal processing and discloses a voice underdetermined blind identification method and device based on frequency spectrum correction and data density clustering to improve algorithm precision, improve algorithm efficiency remarkably and improve the robustness of the algorithm on noise. According to the technical scheme, the method comprises the steps of 1, conducting hanning windowed L point 50% overlapped short time Fourier transform (STFT) to obtain an observation frequency spectrum Xm(t,k); 2, conducting frequency spectrum correction on the STFT observation frequency spectrum frame by frame; 3, for a specific time frame t0, conducting mode purification on all harmonic wave parameters; 4, executing the step 2 and the step 3 frame by frame, and collecting SAS modes of the all the time frames to form a monosource domain omega={zi, i=1,...,P}, wherein P is the number of modes of the monosource domain; 5, conducting data density clustering on the SAS modes in the monosource domain. The method and device are mainly applied to digital signal processing.

Description

technical field [0001] The invention belongs to the technical field of digital signal processing. Specifically, it involves the blind estimation of the mixture matrix for speech signals in the underdetermined situation where the number of observations is less than the number of sources. Background technique [0002] Blind Source Separation (BSS for short) [1] is the process of estimating the channel parameters by only relying on the received observation signal without prior knowledge of the channel, and then recovering the source signal. Its applications involve speech signal processing [2], image processing [3], mechanical fault diagnosis [4], communication channel estimation [5] and other fields, and it is one of the hot issues in the field of signal processing. [0003] According to the relative relationship between the number of source signals and the number of observed signals, blind source separation can be divided into overdetermined case (the number of source signal...

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): G10L21/0272G06K9/62
CPCG10L21/0272G06F18/23
Inventor 黄翔东靳旭康
Owner TIANJIN UNIV
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