Automatic Cluster Complexity and Quantity Selection: Towards Robust Speaker Diarization
The goal of speaker diarization is to determine where each participant speaks in a recording. One of the most commonly used technique is agglomerative clustering, where some number of initial models are grouped into the number of present speakers. The choice of complexity, topology, and the number of initial models is vital to the final outcome of the clustering algorithm. In prior systems, these parameters were directly assigned based on development data, and were the same for all recordings. In this paper we present three techniques to select the parameters individually for each case, obtaining a system that is more robust to changes in the data. Although the choice of these values depends on tunable parameters, they are less sensitive to changes in the acoustic data and to how the algorithm distributes data among the different clusters. We show that by using the three techniques, we achieve an improvement up to 8% relative in the development set and 19% relative in the test set over prior systems.
KeywordsHide Markov Model Bayesian Information Criterion Gaussian Mixture Model Initial Cluster Acoustic Model
Unable to display preview. Download preview PDF.
- 1.Reynolds, D., Torres-Carrasquillo, P.: Approaches and applications of audio diarization. In: ICASSP 2005, Philadelphia, PA, March 2005, pp. 953–956 (2005)Google Scholar
- 2.Chen, S.S., Gopalakrishnan, P.: 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
- 3.Wooters, C., Fung, J., Peskin, B., Anguera, X.: Towards robust speaker segmentation: The ICSI-SRI fall 2004 diarization system. In: Fall 2004 Rich Transcription Workshop (RT 2004), Palisades, NY (November 2004)Google Scholar
- 4.Ajmera, J., Wooters, C.: A robust speaker clustering algorithm. In: ASRU 2003, US Virgin Islands, USA (December 2003)Google Scholar
- 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
- 7.NIST rich transcription evaluations, website: http://www.nist.gov/speech/tests/rt
- 8.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