Multi-channel speech enhancement method based on semantic prior selective attention

A speech enhancement and multi-channel technology, which is applied in speech analysis, instruments, etc., can solve the problems of high noise and complicated situations of the target sound source, and achieve the effect of suppressing interference and noise

Active Publication Date: 2017-03-22
INST OF ACOUSTICS CHINESE ACAD OF SCI
View PDF3 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In reverberant fields with room reflections, the situation is more c

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
  • Multi-channel speech enhancement method based on semantic prior selective attention
  • Multi-channel speech enhancement method based on semantic prior selective attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] There are many features that distinguish the target speech from other sounds, and to make full use of such features for detection, it is necessary to give priority to the features with the most prior knowledge and the most reliable. For example, when a speaker plays a sound, the sound related to the speaker sound can be considered as echo interference; if the semantics of the target speech is known, then the semantics is an obvious distinguishing feature; if the sound wave arrival direction of the target speech (Direction of Arrival, DOA) is known, then detecting DOA information can be used to remove a large number of irrelevant sounds. Through the detection and comparison of various discriminative information, the influence of the sound can be finally suppressed, and the target speech segment can be screened out from the mixed sound.

[0036] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0037] Such as figure...

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 provides a multi-channel speech enhancement method based on semantic prior selective attention. The method comprises the following steps: picking speech signals from any directions in a reverberant environment by virtue of a multi-microphone array, collecting the multiple paths of speech signals and pre-processing the speech signals; detecting special activation words in the pre-processed speech signals by virtue of an activation word speech recognition model; processing signals which are not cut and include activation word segments, so as to obtain a complete activation word segment; analyzing the activation word segment by virtue of a multi-channel phase difference sound localization method based on reverberation robust, so as to obtain an acoustic wave reaching direction of a target sound source; and enhancing speech in the direction and inhibiting noise from other directions and room reverberation in a remote speak scene, so that enhanced speech in the target direction is obtained. The method provided by the invention is applicable to such occasions as intelligent household electrical appliance, smart home, vehicle-mounted and wearable devices and the like that remote speak type speech input and interaction are required, and the method is especially applicable to complex acoustic noise and interference environment occasions.

Description

technical field [0001] The invention relates to the field of speech processing, in particular to a multi-channel speech enhancement method based on semantic prior selective attention. Background technique [0002] With the continuous popularization of voice communication and human-computer voice interaction systems, people are increasingly looking forward to abandoning cumbersome equipment such as microphones and earphones to realize human-machine voice communication that is as natural as human dialogue. However, speech is a sound wave that is affected by various effects when transmitted in the air, such as attenuation of the sound wave, multiple reflections (reverberation) from walls and obstacles, the presence of other sound sources and environmental noise, etc. at the same time. When multiple voice systems and multiple speakers are in the same environment, how to ensure that the system receives voice information correctly determines whether the voice system can be practic...

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): G10L21/02
Inventor 付强王晓飞国雁萌颜永红
Owner INST OF ACOUSTICS CHINESE ACAD OF SCI
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