Voice activity detection over multiresolution subspaces

In this paper, voice activity detection (VAD) is posed as a binary detection problem of an unknown speech signal in both stationary (vehicular) and nonstationary (babble) noise environments. Optimal detection methods are applied on the wavelet transform coefficients of a signal segment to determine...

Full description

Saved in:
Bibliographic Details
Main Authors: Erdol, N., Schultz, R.
Format: Conference Proceeding
Language:English
Subjects:
Covariance matrix
Discrete wavelet transforms
Eigenvalues and eigenfunctions
Energy resolution
Karhunen-Loeve transforms
Noise level
Phase noise
Signal resolution
Speech enhancement
Working environment noise
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, voice activity detection (VAD) is posed as a binary detection problem of an unknown speech signal in both stationary (vehicular) and nonstationary (babble) noise environments. Optimal detection methods are applied on the wavelet transform coefficients of a signal segment to determine the presence of speech. Theoretical analysis is done to justify the effectiveness of multiresolution decomposition on the computation of the noise eigenvalues and vectors and sufficient statistics. VAD results are compared to optimal detection without wavelet transformation and to an energy based method which is used as control. The results show the superiority of the proposed method as increased accuracy in detection.
DOI:10.1109/SAM.2000.878001