Unlock instant, AI-driven research and patent intelligence for your innovation.

Speech detection method and device

A voice detection and voice technology, applied in voice analysis, instruments, etc., can solve the problems of low accuracy, time-consuming and labor-intensive, etc., and achieve the effect of improving efficiency and accuracy

Active Publication Date: 2020-06-23
北京海天瑞声科技股份有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a voice detection method to solve the problems of time-consuming, labor-intensive and low accuracy caused by artificial listening on sampling samples

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
  • Speech detection method and device
  • Speech detection method and device
  • Speech detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. 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.

[0048]In order to cover the acoustic characteristics of all speakers of a certain language in the voice database, it is often necessary to record a large amount of speaker data. Usually, a database may contain thousands of speakers, resulting in the voice database including some people who repeat their voices. question. If the database contains r...

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

An embodiment of the invention provides a speech detection method and apparatus. The method comprises: using a first speech model acquired in advance to acquire a first probability for each test speech in a speech database except a first test speech, wherein the first speech model is used for detecting a probability that a test speech is a speech spoken by a first speaker and the first speaker isa speaker corresponding to the first test speech; according to the first probability of each test speech in the speech database except the first test speech, determining a second test speech spoken bythe same speaker as the first test speech, wherein the second test speech is the test speech with the highest first probability. The method provided by the embodiment detects all the speeches of thesame person in the speech database, and improves efficiency and accuracy.

Description

technical field [0001] Embodiments of the present invention relate to the field of voice detection, and in particular, to a voice detection method and device. Background technique [0002] With the development of speech recognition technology, speech databases are gradually established. In order to cover the acoustic characteristics of all speakers of a language as much as possible, it is necessary to record a large amount of speaker data. Usually, a database may contain thousands of speakers. An issue that caused the voice database to include duplicate voices for some people. [0003] At present, for the voice detection of the same person, manual sampling is used. For example, in a database of 1,000 people, the data of 100 people are randomly selected, and the data of 100 people are manually identified one by one to check whether there are repeated speakers in the data of 100 people. [0004] However, random inspection can only obtain the proportion of repeated speakers in...

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): G10L17/04G10L17/02
CPCG10L17/02G10L17/04
Inventor 邵志明曹琼宋琼郝玉峰
Owner 北京海天瑞声科技股份有限公司