Robust Voice Activity Detector for Real World Applications Using Harmonicity and Modulation Frequency

Abstract

The task of robustly detecting distant speech in low SNR environments for automatic speech recognition is examined using a two-stage approach based on two distinguishing features of speech, namely harmonicity and modulation frequency (MF). A modified metric for harmonicity is used as a gating function to a set of parallel classifiers that incorporate MFs… (More)

Topics

6 Figures and Tables

Cite this paper

@inproceedings{Chuangsuwanich2011RobustVA, title={Robust Voice Activity Detector for Real World Applications Using Harmonicity and Modulation Frequency}, author={Ekapol Chuangsuwanich and James R. Glass}, booktitle={INTERSPEECH}, year={2011} }