Speaker's role separation method and system in trial scene

A separation method and speaker technology, applied in the speaker role separation method and system field, can solve problems such as the inconvenience of listening back and watching, and achieve the effect of ensuring accuracy

Active Publication Date: 2018-05-25
ANHUI IFLYTEK INTELLIGENT SYST
View PDF16 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this kind of interrogation recording equipment has the following disadvantages: whether it is one pickup or multiple pickups, everyone’s voices will be recorded at the same time, which will cause a lot of inconvenience for subsequent playback.

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
  • Speaker's role separation method and system in trial scene
  • Speaker's role separation method and system in trial scene
  • Speaker's role separation method and system in trial scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] In order to enable those skilled in the art to better understand the solutions of the embodiments of the present invention, the embodiments of the present invention will be further described in detail below in conjunction with the drawings and implementations.

[0058] Such as figure 1 As shown, it is a flow chart of the speaker role separation method in the interrogation scene of the embodiment of the present invention, including the following steps:

[0059] Step 101, acquire voice data in an interrogation scene.

[0060] Step 102, extracting character recognition features of each analysis unit from the voice data, each analysis unit only includes one speaker's voice segment.

[0061] Each analysis unit is a complete effective speech segment. Specifically, when each analysis unit is determined, the speech data can be firstly subjected to endpoint detection to obtain each effective speech segment, and then the effective speech segment is segmented , to get each analy...

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 speaker's role separation method and system in a trial scene, and the method comprises the steps: obtaining the voice data in the trial scene; extracting a role recognition feature of each analysis unit from the voice data, wherein each analysis unit just comprises a voice segment of one speaker; sequentially inputting the role recognition features of each analysis unit into a pre-built speaker's role recognition mode, and determining a speaker's role corresponding to the current analysis unit according to the model output, wherein the speaker's role comprises an interrogating person and an interrogated person. According to the invention, the method and system can achieve the accurate recognition of the speaker's role in the trial scene.

Description

technical field [0001] The invention relates to the field of voice signal processing, in particular to a speaker role separation method and system in an interrogation scene. Background technique [0002] At present, a large number of interrogation cases are handled across the country every year, and the procuratorate needs to record the interrogation situation and the content of the questions and answers in detail during the interrogation, and the related work consumes a lot of manpower. At the same time, there are omissions or inaccurate records due to personal reasons, and the development of speech recognition technology provides an effective way to solve this problem. [0003] Most of the current interrogation recordings use ordinary pickup equipment, which may be one or more. The equipment is generally placed on the wall or on the table in the interrogation room to record the voice of the entire interrogation process. However, this interrogation recording device has the...

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): G10L17/02G10L17/04G10L17/00
CPCG10L17/02G10L17/04G10L17/00
Inventor 柳林张程风殷兵顾雷雷谢名亮王建社刘海波胡良义汪睿
Owner ANHUI IFLYTEK INTELLIGENT SYST
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