Signal separation method and deice, equipment and storage medium

A signal separation and sound source signal technology, applied in speech analysis, instruments, etc., can solve the problem of inability to accurately separate the target sound source signal.

Inactive Publication Date: 2019-05-28
BEIJING INTELLIGENT STEWARD CO LTD
View PDF6 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in some specific scenarios, such as when multiple people are in a small space, the existing separation algorithms cannot accurately separate the target sound source signals

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
  • Signal separation method and deice, equipment and storage medium
  • Signal separation method and deice, equipment and storage medium
  • Signal separation method and deice, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Figure 1A It is a flow chart of a signal separation method provided by Embodiment 1 of the present invention. This embodiment is applicable to how to accurately separate each sound source from multiple sound sources, and is especially suitable for multi-sound source scenarios such as conference rooms or vehicles. In the environment, etc., multiple people speak at the same time, or the speaker coexists with multiple noise sources, etc. The method can be executed by the signal separation device provided in the embodiment of the present invention, the device can be implemented in the form of software and / or hardware, and the device can be integrated in a computing device, or can be independently used as a device. see Figure 1A , the method specifically includes:

[0032] S110, according to the angle information in the beamforming algorithm, uniformly divide the circle surrounded by the ring microphone array to obtain each beam sound area.

[0033] In this embodiment, th...

Embodiment 2

[0060] figure 2 It is a flow chart of a signal separation method provided by Embodiment 2 of the present invention. On the basis of Embodiment 1 above, this embodiment further eliminates each preliminary sound source signal according to the principle of echo cancellation, and obtains each preliminary sound source signal. The target sound source signal corresponding to the sound source signal is explained. see figure 2 , the method specifically includes:

[0061] S210, according to the angle information in the beamforming algorithm, uniformly divide the circle surrounded by the ring microphone array to obtain each beam sound area.

[0062] S220, using a voice collection system to collect the mixed original sound source signal, wherein the voice collection system is composed of a ring microphone array.

[0063] S230. Preliminarily separate the mixed original sound source signals, and determine the preliminary sound source signals output by each beam sound area.

[0064] S2...

Embodiment 3

[0073] image 3 It is a flow chart of a signal separation method provided by Embodiment 3 of the present invention. On the basis of the above embodiments, this embodiment further eliminates each preliminary sound source signal according to the principle of echo cancellation, and obtains each preliminary sound source signal. The target sound source signal corresponding to the sound source signal is explained. see image 3 , the method specifically includes:

[0074] S310, according to the angle information in the beamforming algorithm, uniformly divide the circle surrounded by the ring microphone array to obtain each beam sound area.

[0075] S320, using a voice collection system to collect mixed original sound source signals, wherein the voice collection system is composed of a ring microphone array.

[0076] S330. Preliminarily separate the mixed original sound source signals, and determine preliminary sound source signals output by each beam sound area.

[0077]S340, for...

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

Embodiments of the invention disclose a signal separation method and device, equipment and a storage medium. The method is applied in a multi-sound source scene and comprises the steps of: carrying out uniform segmentation on a circumference formed by a ring-shaped microphone array according to angle information in a beam forming algorithm, so as to obtain beam sound areas; acquiring a mixed original sound source signal by adoption of a voice acquisition system, wherein the voice acquisition system is formed by the ring-shaped microphone array; preliminarily separating the mixed original soundsource signal to determine a preliminary sound source signal output by each beam sound area; and cancelling each preliminary sound source signal according to an echo cancellation processing so as toobtain a target sound source signal corresponding to each preliminary sound source signal. According to the method, each target sound source signal can be correctly separated; and the method can be suitable for multi-sound source scenes to provide a new thought for correctly separating each sound source in the multi-sound source scenes.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of voice signal processing, and in particular, to a signal separation method, device, equipment, and storage medium. Background technique [0002] With the development of speech recognition applications, the ability to separate single sound source signals in complex acoustic environments (such as multiple speakers, multiple interference sources, etc.) is increasingly required. Only by separating multiple sound sources can the speech recognition system work normally on the separated single sound source. [0003] At present, blind signal processing has great application value in many fields such as biomedical signal processing, communication, image and voice signal processing. Blind Source Separation (BSS, Blind Source Separation), also known as blind signal separation, refers to how to separate from the aliased signal composed of each original sound source signal when the theoretical mo...

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): G10L21/0272G10L21/028G10L21/0208
Inventor 徐燃刘东强
Owner BEIJING INTELLIGENT STEWARD CO LTD
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