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

Voice separation method and device

A voice separation and voice technology, applied in voice analysis, instruments, etc., can solve problems such as unsatisfactory voice separation effect, and achieve the effect of improving the voice separation effect

Pending Publication Date: 2020-05-12
MIAOZHEN INFORMATION TECH CO LTD
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a hybrid voice separation method and device to at least solve the problem in the related art that the voice separation effect is not ideal in a scene where the background sound changes

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 and device
  • Voice separation method and device
  • Voice separation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] Hereinafter, the present invention will be described in detail with reference to the drawings and examples. It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0022] It should be noted that the terms "first" and "second" in the description and claims of the present invention and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence.

[0023] In this embodiment, a hybrid speech separation method is provided, figure 1 is a flow chart of a method according to an embodiment of the present invention, such as figure 1 As shown, the process includes the following steps:

[0024] Step S102, collect the near audio track and the far audio track respectively through the near-end recording device and the far-end recording device, wherein the near audio track only includes the first voice, and...

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 mixed voice separation method and a device. The mixed voice separation method comprises the steps: respectively collecting a near-end voice track and a far-end voice track through near-end recording equipment and far-end recording equipment, wherein the near-end voice track only comprises first voice, and the far-end voice track is mixed voice comprising the first voice, second voice and environment noise; marking the starting time and the ending time of each recording segment of the first voice in the near-end voice track to obtain a first marking file; and separatingthe mixed voice in the far-end voice audio track according to the first marking file. According to the method and the device, the starting time and the ending time of the first voice are marked, so that the first voice is recognized from the mixed voice, the first voice and the second voice are separated, and the voice separation effect in a complex background voice scene is improved.

Description

technical field [0001] The invention relates to the field of speech processing and recognition, in particular to a speech separation method and device. Background technique [0002] Currently, recorders that require voice separation on the market are mostly used in quiet environments, such as in cars, or in environments with regular background sounds, such as watching TV. The separation method is mostly two-dimensional horizontal placement or one-dimensional horizontal placement. For example, use 2 to 6 MICs to judge the direction and type of sound (human voice, noise) through the propagation speed of sound, so as to separate the voices of people in different directions. (audio track). [0003] However, according to the above separation method, in some complex environments, for example, in a service place, the scene where the background sound changes will lead to the inability to correctly separate the human voice (doped with noise and ambient sound). Contents of the inve...

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): G10L21/0272G10L21/0208G10L21/0216
CPCG10L21/0272G10L21/0208G10L21/0216G10L2021/02165
Inventor 李健徐浩梁志婷
Owner MIAOZHEN INFORMATION 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