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

Human voice separation method, device, terminal and readable storage medium for database building

A separation method and database technology, which is applied in the field of human voice separation in data database construction, can solve the problems of large errors and low efficiency

Active Publication Date: 2022-07-26
SPEAKIN TECH CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The main purpose of the present invention is to provide a human voice separation method, device, terminal and readable storage medium related to data database construction, aiming to solve the technical problems of low efficiency and large errors in the process of voice conference record processing

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
  • Human voice separation method, device, terminal and readable storage medium for database building
  • Human voice separation method, device, terminal and readable storage medium for database building
  • Human voice separation method, device, terminal and readable storage medium for database building

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

[0049]The main solution of the embodiments of the present invention is to detect whether the original voice to be processed is mixed by multiple people, and if the original voice is mixed by multiple people, perform noise reduction processing on the original voice to obtain the first multi-voice Voice, wherein the multi-voice voice is a voice that includes a single voice and a multi-player mix or only includes a multi-player mix, and the first multi-voice voice is divided into several preset duration voice segments according to time series , extracting the single-voice voice existing in each of the voice fragments as the first single-voice voice, and extracting the remaining second multi-voice voice in each of the voice fragments, wherein the single-voice voice is The voice of only one human voice is included, a...

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 method for separating human voices for database building, which detects whether the original voice is mixed by multiple people. Vocal speech, the first multi-voice speech is divided into several preset duration speech segments according to the time sequence, the first single-voice speech in the speech segment is extracted, and the remaining number 1 in each of the speech segments is extracted. Two multi-voice voices, use the frequency of the first single-voice voice as the screening frequency to obtain the second single-voice voice, remove the second single-voice voice to obtain the third multi-voice voice, and use the preset The bisection algorithm separates the third multi-voice voice to obtain the third single-voice voice, and stores all the single-voice voices in the voice database. The invention also discloses a device, a terminal and a readable storage medium. The processing efficiency of the voice conference record is improved, and the error of the voice conference record processing is reduced.

Description

technical field [0001] The present invention relates to the technical field of human voice separation, and in particular, to a human voice separation method, device, terminal and readable storage medium for database building. Background technique [0002] Current meeting recordings come in many forms, such as voice, for meeting review. However, there will be situations such as discussions and arguments during the meeting. This kind of simultaneous speech by many people and other noises will bring huge consequences to the later manual processing of voice meeting records, that is, recording the content of the participants separately. Difficulty, it takes a lot of time to process, and it is difficult for the computer to record the content of the participants separately, and due to the subjectivity of people, it will lead to errors in the processing of voice conference records, resulting in low processing efficiency of voice conference records. , the problem of large errors. ...

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): G10L21/0272G10L25/27
CPCG10L21/0272G10L25/27
Inventor 陈昊亮许敏强杨世清
Owner SPEAKIN 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