Robust end-of-utterance detection for real-time speech recognition applications

@inproceedings{Hariharan2001RobustED,
  title={Robust end-of-utterance detection for real-time speech recognition applications},
  author={Ramalingam Hariharan and Juha H{\"a}kkinen and Kari Laurila},
  booktitle={ICASSP},
  year={2001}
}
In this paper we propose a sub-band energy based end-ofutterance algorithm that is capable of detecting the time instant when the user has stopped speaking. The proposed algorithm finds the time instant at which many enough sub-band spectral energy trajectories fall and stay for a pre-defined fixed time below adaptive thresholds, i.e. a non-speech period is detected after the end of the utterance. With the proposed algorithm a practical speech recognition system can give timely feedback for the… CONTINUE READING
Highly Cited
This paper has 34 citations. REVIEW CITATIONS