Voice activity detection apparatus and method

A voice activity detection and voice activity technology, applied in the field of signal processing, can solve problems such as system performance degradation and inaccurate indication

Inactive Publication Date: 2007-11-28
KK TOSHIBA
View PDF0 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the likelihood ratios calculated with the above technique vary on the order of 60dB or more
If the noise of the input signal varies widely, the threshold will be an inaccurate indicator of the presence of speech and system performance may degrade

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
  • Voice activity detection apparatus and method
  • Voice activity detection apparatus and method
  • Voice activity detection apparatus and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] These and other aspects of the invention will be further described below by way of example with reference to the accompanying drawings.

[0047] In the statistical model used in the present invention (also described in Cho et al.), by testing two hypotheses, H 0 and H 1 , to make a voice activity determination, where, H 0 indicates the absence of speech, while H 1 Indicates the presence of speech.

[0048] The statistical model assumes that each spectral component of speech and noise has a complex Gaussian distribution, where the noise is additive and uncorrelated with speech. Based on this assumption, given H 0,k and H 1,k , noise spectral component (noisy spectral component) X k The conditional probability density function (PDF) of is as follows:

[0049] P ( X k | H 0 , k ...

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

A voice activity detection method comprising the steps of (a) Estimating in a noise power estimator the noise power within a signal having a speech component and a noise component, and (b) Calculating a likelihood ratio for the presence of speech in the signal from the estimated power of noise signals from step (a) and a complex Gaussian statistical model.

Description

technical field [0001] The present invention relates to signal processing, in particular, to a voice activity detection method and a voice activity detector. Background technique [0002] Speech signals sent by voice communication devices are usually corrupted to some extent by noise, which interferes with and degrades the performance of encoding, detection and recognition algorithms. [0003] To detect speech periods in an input signal containing both speech and noise components, various speech activity detectors and detection methods have been developed. The device and method can be applied to fields such as speech coding, speech enhancement and speech recognition. [0004] The simplest form of voice activity detection is an energy-based approach, in which the power of the input signal is estimated (ie, an increase in energy indicating the presence of speech) in order to determine whether speech is present. Such techniques work well when the signal-to-noise ratio is high...

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): G10L11/02G10L25/78
CPCG10L25/78
Inventor F·雅布劳恩
Owner KK TOSHIBA
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