Method and device for voice separation during interrogation

A voice separation and voice technology, applied in voice analysis, instruments, etc., can solve the problem of low efficiency of interrogation transcripts

Active Publication Date: 2020-10-23
BEIJING UNISOUND INFORMATION TECH
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a method and device for voice separation during interrogation, which is used to solve the defect of low efficiency of existing manual recording of interrogation transcripts

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
  • Method and device for voice separation during interrogation
  • Method and device for voice separation during interrogation
  • Method and device for voice separation during interrogation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0059] An embodiment of the present invention provides a method for voice separation during interrogation, based on two audio collection devices (such as microphones, etc.) to achieve the effect of voice separation. Specifically, see figure 1 As shown, the method includes steps 101-103:

[0060] Step 101: Obtain the first voice data collected by the first audio collection device and the second voice data collected by the second audio collection device, the first audio collection device is a device directed to the interrogator, and the second audio collection device is directed to the interrogated person installation.

[0061] In the embodiment of the present inven...

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 an interrogation voice separation method and device. The method includes acquiring first voice data collected by a first audio collection device and second voice data collectedby a second audio collection device, wherein the first audio collection device is a device pointing to an interrogator while the second audio device is a device pointing to an interrogee; performing filtering treatment on the first voice data and determining interrogation voice data corresponding to the interrogator; removing the interrogation voice data in the second voice data by taking the interrogation voice data as reference signals and determining interrogee voice data in the second voice data. According to the invention, interference of an interrogee channel is reduced effectively through two groups of voice data, so that correct separation of voice signals of the interrogator and the interrogee is realized. Then the voices of the interrogator and the interrogee are recognized correctly through voice recognition, and thus a hearing record can be generated automatically. Therefore, the interrogation efficiency is improved and labor cost is reduced.

Description

technical field [0001] The invention relates to the technical field of speech separation, in particular to a method and device for speech separation during interrogation. Background technique [0002] At present, interrogations in judicial scenarios (such as criminal interrogations) are generally generated in the form of transcripts, which are inefficient and need to be done manually, resulting in a waste of manpower and material resources. At the same time, due to the inherent limitations of the interrogation scene, the signals collected by the microphone often contain multiple speaking targets, and direct recognition of the collected voice signals cannot effectively distinguish the speaking targets; The speaking voice is often too low, or even very different, so most of the interrogation process is currently recorded manually. Contents of the invention [0003] The invention provides a method and device for voice separation during interrogation, which are used to solve ...

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 Patents(China)
IPC IPC(8): G10L21/0272G10L17/00G10L17/02
CPCG10L17/00G10L17/02G10L21/0272
Inventor 马金龙关海欣
Owner BEIJING UNISOUND INFORMATION TECH
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