Acoustic echo cancellation techniques for far-end telephony speech recognition in barge-in situations

In this paper, we present some techniques of acoustic echo cancellation for far-end (server-side) telephony speech recognition during barge-in situations. We develop a normalized least mean square algorithm for the adaptive filter of an echo canceller, and a double-talk detector for the online speech recognition services. In particular, we devise a voice activity detector for estimating the initial delay due to communication networks. In addition, we propose a hybrid method that uses the log-spectral distance measure, as well as the cross-correlation coefficients, to estimate the initial delay. From the simulation and the experiments in real environments, we conclude that the developed techniques can be successfully used for far-end telephony speech recognition services.