Model training method and device, voice separation method and device and electronic equipment

A technology for model training and speech separation, which is applied in the fields of devices and electronic equipment, model training methods, and speech separation methods, and can solve problems such as low accuracy of speech separation.

Active Publication Date: 2021-05-18
SOUNDAI TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present disclosure provide a model training method, speech separation method, device, and electronic equipment to solve the problem of segmenting speech based on experience in the prior art, and the split speech segments are likely to contain two or more utterances Human speech, which leads to the problem of low accuracy 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, voice separation method and device and electronic equipment
  • Model training method and device, voice separation method and device and electronic equipment
  • Model training method and device, voice separation method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present disclosure. 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 creative efforts fall within the protection scope of the present invention.

[0028] In the embodiments of the present disclosure, electronic devices include but are not limited to mobile phones, tablet computers, notebook computers, palmtop computers, vehicle-mounted mobile terminals, wearable devices, and pedometers.

[0029] see figure 1 , figure 1 is a schematic flowchart of a model training method provided by an embodiment of the present disclosure, such as figure 1 shown, including the following steps:

[0030] Step 101...

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 model training method and device, a voice separation method and device and electronic equipment, and the method comprises the steps: the voice features of a sound signal are input into N pre-trained first neural network models, and N output results are obtained, wherein the N output results are voice features of the voice of the speaker corresponding to N pickup areas separated from the sound signal, and N is an integer greater than 1; voice features of the sound signals are input into a second neural network model, the second neural network model is trained, and a loss function used for training the second neural network model is determined based on the N output results. According to the embodiment of the invention, voice separation is carried out by adopting the trained second neural network model, so that the accuracy of voice separation can be improved.

Description

technical field [0001] The invention relates to the technical field of speech processing, in particular to a model training method, a speech separation method, a device and electronic equipment. Background technique [0002] Voice is the most natural, convenient and effective way for people to communicate with each other. The voice of interest can be obtained from a large number of voices through voice separation. In the process of speaker separation for speech, it is necessary to segment the speech, and then mark the speaker information for the segmented speech segments. [0003] Currently, speech is segmented based on experience, and the segmented speech segments are likely to contain the speech of two or more speakers, resulting in a low accuracy rate of speech separation. Contents of the invention [0004] Embodiments of the present disclosure provide a model training method, speech separation method, device, and electronic equipment to solve the problem of segmentin...

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): G10L21/028G10L21/0208G10L25/30G06N3/08G06N3/04
CPCG10L21/028G10L21/0208G10L25/30G06N3/08G10L2021/02087G06N3/045
Inventor 陈孝良冯大航赵力常乐
Owner SOUNDAI TECH 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