Title :
Estimation of speech presence probability in the field of microphone array
Author :
Potamitis, Ilyas
Author_Institution :
Wire Commun. Lab., Univ. of Patras, Greece
Abstract :
The subject of this work is the robust estimation of speech presence probability of every spectral component of a speech signal impinging on a linear microphone array. The approach is based on the generalized likelihood ratio test (GLRT) applied to the multichannel framework and far-field, wideband sources. It is shown that under certain distributional assumptions the GLRT provides a framework for speech presence detection by exploiting both the spatial localization and spectral content of the speech signal. The efficiency of the approach and its superiority over a state-of-the-art one-channel speech presence estimation technique is illustrated when additive white Gaussian noise is present in the acoustical field in low signal-to-noise ratio (SNR).
Keywords :
AWGN; microphone arrays; probability; speech processing; GLRT; acoustical field; additive white Gaussian noise; generalized likelihood ratio test; linear microphone array; multichannel framework; speech presence probability estimation; speech signal; voice activity detection; Acoustic noise; Acoustic signal detection; Discrete Fourier transforms; Frequency; Microphone arrays; Sensor arrays; Speech enhancement; Speech processing; Vectors; Wideband; 65; Microphone arrays; speech presence probability; speech processing; voice activity detection;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2004.838200