431324

Hybrid Speaker-Based Segmentation System Using Model-Level Clustering

Kim, Hyoung-Gook ; Ertelt, Daniel ; Sikora, Thomas

Commun. Syst. Inst., Tech. Univ. of Berlin, Germany

1

2005

March 18-23, 2005

745

748

Bayes methods; hidden Markov models; speaker recognition; Bayesian information criterion; HMM model scores; hybrid speaker-based segmentation system; metric-based segmentation; model-based segmentation; model-level clustering; resegmentation step; speaker identification; speech recognition; two-level clustering algorithm; Algorithm design and analysis; Bayesian methods; Change detection algorithms; Clustering algorithms; Feature extraction; Hidden Markov models; Loudspeakers; Merging; Robust stability; Speech;

English

ieee

Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on

1520-6149

0-7803-8874-7

conf

10.1109/ICASSP.2005.1415221

1415221