Speech enhancement method and system, computer equipment and storage medium

A voice enhancement and target voice technology, applied in computer equipment and storage media, in the field of voice enhancement based on acoustic vector sensors and deep neural networks, can solve the problems of high hardware cost, large acquisition system volume, and high computational complexity

Active Publication Date: 2019-11-26
PEKING UNIV SHENZHEN GRADUATE SCHOOL
View PDF7 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

According to different audio collection devices, speech enhancement technology can be divided into single-channel and multi-channel speech enhancement. Among them, multi-channel speech enhancement has the advantages of more effective suppression of environmental noise and reverberation, but has the advantages of high hardware cost, large acquisition system volume, High computational complexity and other limitations

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
  • Speech enhancement method and system, computer equipment and storage medium
  • Speech enhancement method and system, computer equipment and storage medium
  • Speech enhancement method and system, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0077] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0078] The present embodiment provides a method for speech enhancement based on an acoustic vector sensor and a deep neural network. The method uses an acoustic vector sensor (Acoustic Vector Sensor, AVS) to collect audio signals. In remote speech applications, four sensors of the AVS are considered to have In the same spatial position, the four sensors of AVS collect and output four-channel voice signals synchronously. Usually AVS selects the pressure sensor as the omnidirectional sensor, the particle velocity sensor an...

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 speech enhancement method and system, computer equipment and a storage medium, and relates to the technical field of the human-machine speech interaction. The method comprisesthe following steps: collecting multi-channel acoustic signals through an acoustic vector sensor, preprocessing the multi-channel acoustic signals and acquiring a time-frequency spectrum, filtering the time-frequency spectrum and outputting a signal atlas; performing masking processing on the signal atlas through a nonlinear mask, and outputting an enhanced single-channel speech spectrogram; inputting the single-channel spectrogram into a deep neural network mask estimation model and outputting a mask spectrogram; performing time-frequency masking enhancement on the signal atlas through the mask spectrogram to acquire enhanced amplitude speech spectrogram; reconstructing through the enhanced amplitude speech spectrogram so as to output an enhanced target speech signal. The technical problem that the multi-channel speech enhancement is high in hardware cost, large in collection system volume, and high in operation complexity is solved, and the excellent speech enhancement effect can beacquired under difference interference noise types, strengths and room reverberation conditions.

Description

technical field [0001] The invention relates to the technical field of human-computer voice interaction, in particular to a voice enhancement method, system, computer equipment and storage medium based on an acoustic vector sensor and a deep neural network. Background technique [0002] Speech enhancement technology is an important research direction of speech signal processing and one of the core technologies of speech processing systems. It has a wide range of applications in mobile phones, hearing aids, service robots and smart homes. The purpose of speech enhancement is to suppress non-target speech and noise interference signals in the collected multi-channel acoustic signal, and at the same time enhance the target speech signal, thereby improving the intelligibility of speech and improving the performance of the speech recognition system. According to different audio collection devices, speech enhancement technology can be divided into single-channel and multi-channel ...

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): G10L21/0208G10L21/0216G10L25/30G10L25/03
CPCG10L21/0208G10L21/0216G10L25/30G10L25/03G10L2021/02082G10L2021/02166
Inventor 邹月娴刘钊祎张皓然
Owner PEKING UNIV SHENZHEN GRADUATE SCHOOL
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