Advertisement

Robust Speaker Diarization for Meetings: ICSI RT06S Meetings Evaluation System

  • Xavier Anguera
  • Chuck Wooters
  • Jose M. Pardo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4299)

Abstract

In this paper we present the ICSI speaker diarization system submitted for the NIST Rich Transcription evaluation (RT06s) [1] conducted on the meetings environment. The presented system is based on the RT05s system, which uses agglomerative clustering with a modified Bayesian Information Criterion (BIC) measure to decide which pairs of clusters to merge and to determine when to stop merging clusters. In this year’s system we have eliminated any remaining need for training data, therefore increasing robustness. In our primary system we have introduced several improvements from last year. First, we use a new training-free speech/non-speech detection algorithm. Second, we introduce a new algorithm for system initialization. The third improvement is the use of a frame purification algorithm to increase cluster discriminability. Finally, we describe the use of inter-channel delays as features. We explain each of these improvements and show our system’s results on the official evaluation data using hand-aligned references and forced-alignments. We also analyze some of the results and propose improvements.

Keywords

Bayesian Information Criterion Automatic Speech Recognition Acoustic Model Acoustic Data Conference Room 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    NIST rich transcription evaluations, website: http://www.nist.gov/speech/tests/rt
  2. 2.
    Istrate, D., Fredouille, C., Meignier, S., Besacier, L., Bonastre, J.-F.: NIST RT05S evaluation: Pre-processing techniques and speaker diarization on multiple microphone meetings. In: NIST 2005 Spring Rich Transcrition Evaluation Workshop, Edinburgh, UK (July 2005)Google Scholar
  3. 3.
    Cassidy, S.: The macquarie speaker diarization system for RT05S. In: NIST 2005 Spring Rich Transcrition Evaluation Workshop, Edinburgh, UK (July 2005)Google Scholar
  4. 4.
    van Leeuwen, D.: The TNO speaker diarization system system for NIST RT05s for meeting data. In: NIST 2005 Spring Rich Transcrition Evaluation Workshop, Edinburgh, UK (July 2005)Google Scholar
  5. 5.
    Anguera, X., Wooters, C., Peskin, B., Aguilo, M.: Robust speaker segmentation for meetings: The ICSI-SRI spring 2005 diarization system. In: RT05s Meetings Recognition Evaluation, Edinburgh, Great Brittain (July 2005)Google Scholar
  6. 6.
    Ajmera, J., Wooters, C.: A robust speaker clustering algorithm. In: ASRU 2003, US Virgin Islands, USA (December 2003)Google Scholar
  7. 7.
    Anguera, X., Wooters, C., Hernando, J.: Automatic cluster complexity and quantity selection: Towards robust speaker diarization. In: Renals, S., Bengio, S., Fiscus, J.G. (eds.) MLMI 2006. LNCS, vol. 4299, pp. 248–256. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  8. 8.
    Anguera, X., Wooters, C., Hernando, J.: Speaker diarization for multi-party meetings using acoustic fusion. In: IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Puerto Rico, USA (November 2005)Google Scholar
  9. 9.
    Anguera, X., Aguilo, M., Wooters, C., Nadeu, C., Hernando, J.: Hybrid speech/non-speech detector applied to speaker diarization of meetings. In: Speaker Odyssey 2006, Puerto Rico, USA (June 2006)Google Scholar
  10. 10.
    Anguera, X., Wooters, C., Hernando, J.: Friends and enemies: A novel initialization for speaker diarization. In: Proc. ICSLP, Pittsburgh, USA (September 2006) (to appear)Google Scholar
  11. 11.
    Anguera, X., Wooters, C., Hernando, J.: Purity algorithms for speaker diarization of meetings data. In: ICASSP, Toulouse, France (May 2006)Google Scholar
  12. 12.
    Shaobing Chen, S., Gopalakrishnan, P.S.: Speaker, environment and channel change detection and clustering via the bayesian information criterion. In: Proceedings DARPA Broadcast News Transcription and Understanding Workshop, Virginia, USA (February 1998)Google Scholar
  13. 13.
    Pardo, J.M., Anguera, X., Wooters, C.: Speaker diarization for multiple distant microphone meetings: Mixing acoustic features and inter-channel time differences. In: Proc. ICSLP (September 2006)Google Scholar
  14. 14.
    Janin, A., Stolcke, A., Anguera, X., Boakye, K., Cetin, O., Frankel, J., Zheng, J.: The ICSI-SRI spring 2006 meeting recognition system. In: Proceedings of the Rich Transcription 2006 Spring Meeting Recognition Evaluation, Washington, USA (May 2006)Google Scholar
  15. 15.
    Stolcke, A., Anguera, X., Boakye, K., Cetin, O., Grezl, F., Janin, A., Mandal, A., Peskin, B., Wooters, C., Zheng, J.: Further progress in meeting recognition: The icsi-sri spring 2005 speech-to-text evaluation system. In: RT05s Meetings Recognition Evaluation, Edinburgh, Great Brittain (July 2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Xavier Anguera
    • 1
    • 2
  • Chuck Wooters
    • 1
  • Jose M. Pardo
    • 1
    • 3
  1. 1.International Computer Science InstituteBerkeleyUSA
  2. 2.Technical University of CataloniaBarcelonaSpain
  3. 3.Universidad Politecnica de MadridMadridSpain

Personalised recommendations