A Speech Enhancement Method of Small Aperture Array Microphone

A speech enhancement, small aperture technology, applied in speech analysis, instruments, etc., can solve problems such as large amount of calculation, complex method, and complicated calculation, and achieve the effect of small amount of calculation, good noise suppression capability, and good noise suppression performance.

Inactive Publication Date: 2016-02-24
LIAONING UNIVERSITY OF TECHNOLOGY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In the prior art, the microphone array speech enhancement method combining the fourth-order cross cumulant and the linear constrained minimum variance beamforming needs to estimate the direction vector of the speech signal in advance, which makes the calculation of the whole process more complicated. Fixed beamforming, independent component analysis Although the method of combining algorithm and post-filtering technology effectively suppresses the noise, the method is too complicated and requires a lot of calculation

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
  • A Speech Enhancement Method of Small Aperture Array Microphone
  • A Speech Enhancement Method of Small Aperture Array Microphone
  • A Speech Enhancement Method of Small Aperture Array Microphone

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0071] Specific embodiment: the experiment is carried out in an environment with reverberation and noise, and a uniform linear array is formed by 4 microphones with a spacing of 10cm. ), the noise source is located at (5m, 3.5m, 1.5m), the sampling frequency is 16kHz, and the reverberation model of the room adopts the Image model.

[0072] Table 1 Statistical table of different noise SNR

[0073]

[0074] It can be seen from Table 1 that this method has a better ability to suppress noise and can obtain very good results in both coherent noise field and incoherent noise field environments.

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 method for enhancing microphone voice through a small-bore array. According to the method, under the situation that priori knowledge such as a voice signal DOA and an array topological structure is unknown, according to the FastICA basic principle, an objective function with a separation matrix as a variable is built for an output variable, the output variable is maximized, independent isolated components are separated, and then post-processing is conducted. In the process, estimation on a voice source signal direction is removed, and calculated amount is saved.

Description

technical field [0001] The present invention relates to a space-time domain speech enhancement method, more specifically, to a small-aperture linear array blind beamforming speech enhancement method. Background technique [0002] In today's popular video conferencing, teleconferencing and other intelligent voice communication systems, due to the influence of reverberation, environmental noise and interference, the quality of the voice signal picked up by the microphone array will deteriorate , and this will directly affect the performance of speech coding and speech recognition systems. Therefore, effective noise suppression is required. [0003] Chinese patent application number 200910132345.1 discloses a method and device for speech enhancement. Wherein, the method includes: transforming the noisy speech signal to obtain the noisy speech signal in the frequency domain; setting the spectral variance of the previous frame and the square of the spectral amplitude of the pre...

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 Patents(China)
IPC IPC(8): G10L21/0208
Inventor 王冬霞秦亚光梅亚男刘艳军
Owner LIAONING UNIVERSITY OF TECHNOLOGY
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