In this paper we develop a voice activity detection algorithm based on the likelihood that only noise is present in the current signal frame. For this we exploit the fact that the Fourier coefficients of most noise processes can be modeled as statistically independent Gaussian random variables. We also give an overview of different voice activity detectors previously described in the literature and compare their results to the ones obtained with the voice activity detector we propose in this paper. According to our tests, at high speech detection probabilities, the proposed algorithm shows results than are comparable to or better than the other voice activity detectors we consider, while the simplicity of the algorithm ensures low computational complexity.
Dekens, T, Demol, M, Verhelst, W & Beaugendre, F 2007, Voice Activity Detection based on Inverse Normalized Noise Likelihood Estimation. in XIII-th Convention of Electrical Engineering, CIE 2007. Finds and Results from the Swedish Cyprus Expedition: A Gender Perspective at the Medelhavsmuseet, Stockholm, Sweden, 21/09/09. <http://www.etro.vub.ac.be/Research/DSSP/PUB_FILES/int_conf/CEE-2007-tdekens.pdf>
Dekens, T., Demol, M., Verhelst, W., & Beaugendre, F. (2007). Voice Activity Detection based on Inverse Normalized Noise Likelihood Estimation. In XIII-th Convention of Electrical Engineering, CIE 2007 http://www.etro.vub.ac.be/Research/DSSP/PUB_FILES/int_conf/CEE-2007-tdekens.pdf
@inproceedings{7bffcd07f501471b836d28edf6745b5d,
title = "Voice Activity Detection based on Inverse Normalized Noise Likelihood Estimation",
abstract = "In this paper we develop a voice activity detection algorithm based on the likelihood that only noise is present in the current signal frame. For this we exploit the fact that the Fourier coefficients of most noise processes can be modeled as statistically independent Gaussian random variables. We also give an overview of different voice activity detectors previously described in the literature and compare their results to the ones obtained with the voice activity detector we propose in this paper. According to our tests, at high speech detection probabilities, the proposed algorithm shows results than are comparable to or better than the other voice activity detectors we consider, while the simplicity of the algorithm ensures low computational complexity.",
keywords = "Noise estimation, Speech enhancement, Voice activity detection",
author = "Tomas Dekens and Mike Demol and Werner Verhelst and Fr{\'e}d{\'e}ric Beaugendre",
year = "2007",
month = jun,
day = "18",
language = "English",
booktitle = "XIII-th Convention of Electrical Engineering, CIE 2007",
note = "Finds and Results from the Swedish Cyprus Expedition: A Gender Perspective at the Medelhavsmuseet ; Conference date: 21-09-2009 Through 25-09-2009",
}