Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Model training method and device and voice signal processing method and device

A model training and voice signal technology, applied in the computer field, can solve the problems of incapable of real data voice separation processing and the decline of voice separation effect.

Inactive Publication Date: 2021-09-10
BEIJING CENTURY TAL EDUCATION TECH CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The inventors of the present disclosure have found the following problems in the above-mentioned related technologies: it is impossible to perform accurate speech separation processing on real data, resulting in a decline in the effect of speech separation

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
  • Model training method and device and voice signal processing method and device
  • Model training method and device and voice signal processing method and device
  • Model training method and device and voice signal processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. 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.

[0037] At the same time, it should be understood that, for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0038] The following description of at least one exemplary embodiment is merely illustrative in nature and in no way intended as any limitation of the disclosure, its application or uses.

[0039] Techniques, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, techniques, methods and devices should be considered part of the de...

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 relates to a model training method and device and a voice signal processing method and device, and relates to the technical field of computers. The model training method comprises the steps that a teacher model is used for conducting voice separation processing on a mixed voice signal in a first real data set, the mixed voice signal in the first real data set does not have a label, and the teacher model is used for conducting training through a first synthetic data set, and the mixed voice signal in the first synthetic data set has a label; the label of the mixed voice signal in the first real data set is generated according to a voice separation processing result; according to the first real data set and the corresponding label thereof, and the first synthetic data set and the corresponding label thereof, a first student model for voice separation processing is trained; and the teacher model is trained again by using the trained first student model until a training ending condition is met.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular to a model training method, a model training device, a voice signal processing method, a voice signal processing device, and a non-volatile computer-readable storage medium. Background technique [0002] Speech separation technology is a long-standing research direction in the audio field. The human brain is able to extract the sound source of interest in a noisy environment and block the interference of other noises, which is called the cocktail party effect. How to make the machine also have the selectivity of the human brain, and can separate each original audio from the mixed audio, this is the problem solved by the speech separation technology. [0003] For example, beamforming algorithms can be used to separate sound sources from different directions by using the spatial information of the microphone array; signal processing algorithms such as independent compo...

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): G10L21/0272G10L21/0308G06N20/00G06K9/62G06F16/683G06F16/68
CPCG10L21/0272G10L21/0308G06F16/683G06F16/686G06N20/00G06F18/214
Inventor 龚亚光
Owner BEIJING CENTURY TAL EDUCATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com