Title :
Unsupervised Speech Activity Detection Using Voicing Measures and Perceptual Spectral Flux
Author :
Sadjadi, Seyed Omid ; Hansen, John H. L.
Author_Institution :
Dept. of Electr. Eng., Univ. of Texas at Dallas, Richardson, TX, USA
Abstract :
Effective speech activity detection (SAD) is a necessary first step for robust speech applications. In this letter, we propose a robust and unsupervised SAD solution that leverages four different speech voicing measures combined with a perceptual spectral flux feature, for audio-based surveillance and monitoring applications. Effectiveness of the proposed technique is evaluated and compared against several commonly adopted unsupervised SAD methods under simulated and actual harsh acoustic conditions with varying distortion levels. Experimental results indicate that the proposed SAD scheme is highly effective and provides superior and consistent performance across various noise types and distortion levels.
Keywords :
acoustic signal detection; audio signal processing; distortion; speech processing; acoustic condition; audio-based surveillance; distortion level; monitoring application; noise type; perceptual spectral flux; speech application; speech voicing measures; unsupervised SAD method; unsupervised speech activity detection; Correlation; Feature extraction; Hidden Markov models; Noise; Noise measurement; Robustness; Speech; Clarity; Combo-SAD; harmonicity; perceptual spectral flux; speech activity detection; voicing measures;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2013.2237903