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

Self-adaption endpoint detection method using short-time time-frequency value

An endpoint detection and self-adaptation technology, applied in speech analysis, instruments, etc.

Inactive Publication Date: 2014-09-03
XIAMEN UNIV
View PDF5 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0013] The purpose of the present invention is to provide an adaptive endpoint detection method using short-time time-frequency values ​​for the short speech characteristics in the speaker recognition system and the defects of existing endpoint detection methods

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
  • Self-adaption endpoint detection method using short-time time-frequency value
  • Self-adaption endpoint detection method using short-time time-frequency value
  • Self-adaption endpoint detection method using short-time time-frequency value

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] The self-adaptive endpoint detection method using the short-time time-frequency value provided by the present invention is applied in the text-related speaker recognition system of short speech. The input of the system is a PCM audio compression format, a frequency of 8K, and a sampling number of 16 bit, mono, audio file in wav file format. The purpose of the present invention is to detect the speech signal and accurately extract the start and end points of the effective speech segment, thereby improving the recognition performance of the system and reducing the recognition time.

[0072] Voice endpoint detection process provided by the present invention is as follows figure 1 shown. The specific steps are as follows:

[0073] (1) After the voice signal is input, use conventional methods to analyze the audio file and extract digital sampling values. During this period, the analog continuous voice signal is converted into a discrete digital signal by sampling and quant...

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 self-adaption endpoint detection method using a short-time time-frequency value and relates to a voice detection technology in a speaker recognition system. The self-adaption endpoint detection method comprises the following steps: after inputting a voice signal, analyzing a voice file and extracting a sampling value; pre-processing an obtained voice sampling sequence; dividing a pre-processed signal into frames with fixed lengths to form a frame sequence; aiming at data of each frame, extracting three voice signal characteristic parameters of relative values of short-time energy, short-time information entropy and a short-time range; calculating the short-time time-frequency value of each frame of the signal according to the three voice signal characteristic parameters to form a short-time time-frequency value sequence; analyzing a short-time time-frequency value sequence from the first frame of the signals, and finding a starting point and a finishing point of voices and outputting a voice endpoint detection result. The starting point and the finishing point of the voices can be accurately detected under complicated background noises; the recognition accuracy of the system is improved, the recognition time is shortened and the performance of the speaker recognition system under a complicated environment is improved.

Description

technical field [0001] The invention relates to a speech detection technology in a speaker recognition system, in particular to an adaptive endpoint detection method using short-time time-frequency values. Background technique [0002] Speech endpoint detection technology is the first key technology faced in the speaker recognition system. Endpoint detection technology in speech signal processing refers to determining the start and end points of speech from a signal containing speech. As a complete speaker recognition system, its final effect not only depends on the quality of the recognition algorithm, but also many other related factors will directly affect the success of the system application. In the speaker recognition system, the object of processing is the speech signal, but the speech signal in the actual environment has certain background noise. How to effectively distinguish background noise and speech, and remove background noise without speech components as muc...

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
IPC IPC(8): G10L17/02
Inventor 洪青阳雷文钿童峰
Owner XIAMEN UNIV
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