Kernel-Based Speaker Clustering for Rapid Speaker Adaptation

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 classic...

Full description

Saved in:
Bibliographic Details
Main Authors: Yadkoori, Oldooz Hazrati, Ahadi, Seyed Mohammad, Sadjadi, Seyed Omid
Format: Conference Proceeding
Language:English
Subjects:
Clustering algorithms
Clustering methods
Hidden Markov models
Information technology
Kernel
Kernel method
Lagrangian functions
Loudspeakers
Maximum likelihood linear regression
one-class SVM
Speaker Adaptation
Speaker clustering
Speech processing
Support vector machines
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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).
DOI:10.1109/ITNG.2008.176