Supercharge Your Innovation With Domain-Expert AI Agents!

End point detection method for voice without leading mute segment

A technology of endpoint detection and silent segment, applied in speech analysis, instruments, etc., can solve problems such as unavailability, endpoint errors, and performance degradation of double-threshold algorithms

Active Publication Date: 2016-08-03
DALIAN UNIV OF TECH
View PDF5 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the speech signal has no leading silence segment, the performance of the double-threshold algorithm degrades rapidly, because the threshold-based method needs to determine the threshold first, and assume that the first few frames of the signal are noise signals that do not contain speech
In the process of voice endpoint detection, there may be a piece of voice without a leading silence segment or a leading silence segment is relatively short, then the voice threshold will be set incorrectly, so if the voice signal does not meet this assumption, the predefined threshold will be unavailable Yes, endpoint detection will fail

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
  • End point detection method for voice without leading mute segment
  • End point detection method for voice without leading mute segment
  • End point detection method for voice without leading mute segment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The present invention will be further described below in conjunction with accompanying drawing.

[0056] Such as figure 1 Shown, a kind of endpoint detection method of voice without leading silence section, comprises the following steps:

[0057] Step 1, adopting the LMS adaptive algorithm to filter the noisy speech, specifically including the following sub-steps:

[0058] (a), there is a speech signal s(n) and a noise signal source v 0 (n), it can be considered that the noise source v 0 (n) In the process of propagating to the human ear, a filter with a transfer function of H is passed through, and the output is v 1 The signal of (n) is superimposed on the speech signal to obtain a noisy speech d(n),

[0059] d(n)=s(n)+v 1 (n)(1)

[0060] (b), equipped with LMS adaptive filter from another close to the noise signal source v 0 It is filtered at (n), and the filtered signal is y(n), the LMS adaptive filter is used to simulate the filter whose transfer function in ...

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 relates to an end point detection method for voice without a leading mute segment, and belongs to the technical field of voice signal processing. The method comprises the following steps that S1) an LMS adaptive algorithm is used to filter the voice with noise; 2) the de-noised voice is changed from the time domain to the frequency domain; 3) an MFCC parameter of each frame is calculated; 4) the spectral entropy of each frame is calculated; 5) FCM is used to classify voice signals; and 6) the average spectral entropy of each classification in the step 5) is calculated, and voice signals and noise signals are marked. According to the method of the invention, it is not required to set a threshold, and end point detection error caused by that the threshold is set wrongly can be avoided; and compared with a monitored clustering method via a neural network and the like, sample training is not needed, calculation is simple and rapid, and the method is conducive to design of a real-time voice recognition system subsequently.

Description

technical field [0001] The invention relates to a method for detecting an endpoint of a speech without a leading silent segment, and belongs to the technical field of speech signal processing. Background technique [0002] With the development of human-computer information interaction technology, speech recognition technology shows its importance. In speech recognition system, speech endpoint detection is one of the key technologies in speech recognition. Speech endpoint detection refers to finding the starting point and ending point of the speech part in the noisy continuous sound signal. Whether the endpoint detection is accurate or not will directly affect the performance of the speech recognition system. An effective endpoint detection method can not only detect voice endpoints correctly, but also reduce data processing time, save storage space and improve efficiency. [0003] Due to different requirements, such as calculation accuracy, algorithm complexity, robustnes...

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): G10L25/87G10L25/24
CPCG10L25/24G10L25/87
Inventor 董明张超
Owner DALIAN UNIV OF TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com