- 著者
-
Takafumi KOSHINAKA
Kentaro NAGATOMO
Koichi SHINODA
- 出版者
- The Institute of Electronics, Information and Communication Engineers
- 雑誌
- IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
- 巻号頁・発行日
- vol.E95-D, no.10, pp.2469-2478, 2012-10-01
A novel online speaker clustering method based on a generative model is proposed. It employs an incremental variant of variational Bayesian learning and provides probabilistic (non-deterministic) decisions for each input utterance, on the basis of the history of preceding utterances. It can be expected to be robust against errors in cluster estimation and the classification of utterances, and hence to be applicable to many real-time applications. Experimental results show that it produces 50% fewer classification errors than does a conventional online method. They also show that it is possible to reduce the number of speech recognition errors by combining the method with unsupervised speaker adaptation.