Fifth International Conference on Information Technology: New Generations (itng 2008) Kernel-Based Speaker Clustering for Rapid Speaker Adaptation April 07-April 09 ISBN: 978-0-7695-3099-4
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ITNG.2008.176
Speaker clustering is a widely used technique in speaker adaptation, especially since it can be easily combined with adaptation methods such as MAP or MLLR. In this paper we present and evaluate a new speaker adaptation method using a kernel-based speaker clustering algorithm inspired by the classical K-means and based on one-class support vector machines. We find that this adaptation method outperforms other conventional clustering techniques such as K-means and gender clustering with only small amounts of adaptation data (i.e. less than 10 sec).
Index Terms:
Speaker Adaptation, Kernel method, one-class SVM, Speaker clustering
Citation:
Oldooz Hazrati Yadkoori, Seyed Mohammad Ahadi, Seyed Omid Sadjadi, "Kernel-Based Speaker Clustering for Rapid Speaker Adaptation," itng, pp.1287-1289, Fifth International Conference on Information Technology: New Generations (itng 2008), 2008 Usage of this product signifies your acceptance of the Terms of Use. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb