On the use of GSV-SVM for Speaker Diarization and Tracking

@inproceedings{Le2010OnTU,
  title={On the use of GSV-SVM for Speaker Diarization and Tracking},
  author={Viet Bac Le and Claude Barras and Marc Ferras},
  booktitle={Odyssey},
  year={2010}
}
In this paper, we present the use of Gaussian Supervectors wi th Support Vector Machines classifiers (GSV-SVM) in an acoustic speaker diarization and a speaker tracking system, compared with a standard Gaussian Mixture Model system based on adapted Universal Background Models (GMM-UBM). GSVSVM systems (which share the adaptation step with the GMMUBM systems) are observed to have comparable performances: for acoustic speaker diarization, the GMM-UBM system outperforms the GSV-SVM system on… CONTINUE READING

From This Paper

Figures, tables, results, connections, and topics extracted from this paper.
7 Extracted Citations
14 Extracted References
Similar Papers

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 14 references

The CLEAR’07 LIMSI System for Acoustic Speaker Identification in Seminars”, CLEAR’07

  • C. Barras
  • 2007
1 Excerpt

Improve - ments in MLLR - Transform - Based Speaker Recognition ”

  • L. Ferrer, S. Kajarekar
  • Odyssey ’ 06
  • 2006

Similar Papers

Loading similar papers…