Never-ending learning system for on-line speaker diarization

  title={Never-ending learning system for on-line speaker diarization},
  author={Konstantin Markov and Satoshi Nakamura},
  journal={2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)},
In this paper, we describe new high-performance on-line speaker diarization system which works faster than real-time and has very low latency. It consists of several modules including voice activity detection, novel speaker detection, speaker gender and speaker identity classification. All modules share a set of Gaussian mixture models (GMM) representing pause, male and female speakers, and each individual speaker. Initially, there are only three GMMs for pause and two speaker genders, trained… CONTINUE READING
Highly Cited
This paper has 29 citations. REVIEW CITATIONS
20 Citations
23 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 20 extracted citations


Publications referenced by this paper.

Similar Papers

Loading similar papers…