In this paper, we propose a novel frequency-domain approach to double-talk detection based on the Gaussian mixture model. In contrast to a previous approach based on a simple and heuristic decision rule utilizing time-domain cross-correlations, GMM is applied to a set of feature vectors extracted from the frequency-domain cross-correlation coefficients. Performance of the proposed approach is evaluated through objective tests under various environments, and better results are obtained as compared to the time-domain method.
Bibliographic reference. Song, Ji-Hyun / Lee, Kyu-Ho / Park, Yun-Sik / Kang, Sang-Ick / Chang, Joon-Hyuk (2010): "On using Gaussian mixture model for double-talk detection in acoustic echo suppression", In INTERSPEECH-2010, 2778-2781.