Voice separation method, device, medium and equipment

A voice separation and variance technology, applied in electronic equipment, voice separation devices, and voice separation fields, can solve problems such as decline, and achieve the effect of ensuring accuracy, ensuring real-time performance, and improving accuracy

Active Publication Date: 2019-11-08
NANJING INST OF ADVANCED ARTIFICIAL INTELLIGENCE LTD
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The performance of existing speech separation algori

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 separation method, device, medium and equipment
  • Voice separation method, device, medium and equipment
  • Voice separation method, device, medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] Example embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited by the exemplary embodiments described here.

[0022] It should be noted that relative arrangements of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.

[0023] Those skilled in the art can understand that terms such as "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, etc. necessary logical sequence.

[0024] It should also be understood that in the embodiments of the present disclosure, "plurality...

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 voice separation method, device, medium and equipment. The method includes: acquiring a time-frequency domain mixed signal to be processed; performing voice separation processing on the to-be-processed time-frequency domain mixed signal, and obtaining a desired signal variance of the to-be-processed time-frequency domain mixed signal according to a result of the voice separation processing; performing de-reverberation processing on the to-be-processed time-frequency domain mixed signal according to the desired signal variance of the to-be-processed time-frequency domain mixed signal, so as to obtain a de-reverberation time-frequency domain mixed signal; and obtaining a time-frequency domain signal of each sound source according to the time-frequency domain mixed signal after de-reverberation. The technical solution provided by the invention is beneficial to realizing online voice separation in a high reverberation environment for a micro double microphone, isbeneficial to improving accuracy of voice separation and is beneficial to facilitating the real-time performance of voice separation.

Description

technical field [0001] The disclosure relates to speech processing technology, in particular to a speech separation method, a speech separation device, a storage medium and electronic equipment. Background technique [0002] Speech separation technology can extract the original sound source signal from the mixed signal of multiple sound sources, so as to realize the enhancement of the desired signal. At present, speech separation technology has been used in various applications such as smart home systems, video conferencing systems, and speech recognition systems. [0003] The performance of existing speech separation algorithms usually drops significantly in a reverberant environment. How to ensure the performance of the speech separation algorithm in a reverberant environment without causing a substantial increase in the amount of calculation to ensure the real-time performance of speech separation is a technical issue worthy of attention. Contents of the invention [...

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): G10L21/0272
CPCG10L21/0272
Inventor 向腾卢晶
Owner NANJING INST OF ADVANCED ARTIFICIAL INTELLIGENCE 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