Speaker change detection using a new weighted distance measure

@inproceedings{Kwon2002SpeakerCD,
  title={Speaker change detection using a new weighted distance measure},
  author={Soonil Kwon and Shrikanth Narayanan},
  booktitle={INTERSPEECH},
  year={2002}
}
Speaker change detection is a key pre-requisite to speaker tracking and speaker adaptation. It detects the points where a speaker identity changes in a multi-speaker audio stream. We first extract the speech segments from an audio stream by segmentation and classification techniques. Using the extracted speech segments, the proposed weighted metric-based technique detects the speaker change points. New weights are originated from Fisher Linear Discriminant Analysis and, when used with Mel… CONTINUE READING
Highly Cited
This paper has 50 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 32 extracted citations

fewer than 50 Citations

051015'05'08'11'14'17
Citations per Year
Semantic Scholar estimates that this publication has 50 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-6 of 6 references

An Investigation of Automatic io Classification and Segmentation ”

  • T. Hankinson
  • Proceedings of LP
  • 2000

A Weighted imum Distance Classifier for Pattern Recognition ” ,

  • A. N. Venetsanopoulos
  • adian Conference on Electrical and Computer…
  • 1993

Speaker , ironment and Channel Change Detection and Clustering the Bayesian Information Criterion ”

  • P. S. Gopalakrishnan
  • DARPA Broadcast s Transcription and Understanding…

Similar Papers

Loading similar papers…