12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Integrated Online Speaker Clustering and Adaptation

C. Breslin, K. K. Chin, M. J. F. Gales, Kate Knill

Toshiba Research Europe Ltd., UK

For many applications, it is necessary to produce speech transcriptions in a causal fashion. To produce high quality transcripts, speaker adaptation is often used. This requires online speaker clustering and incremental adaptation techniques to be developed. This paper presents an integrated approach to online speaker clustering and adaptation which allows efficient clustering of speakers using the same accumulated statistics that are normally used for adaptation. Using a consistent criterion for both clustering and adaptation should yield gains for both stages. The proposed approach is evaluated on a meetings transcription task using audio from multiple distant microphones. Consistent gains over standard clustering and adaptation were obtained.

Full Paper

Bibliographic reference.  Breslin, C. / Chin, K. K. / Gales, M. J. F. / Knill, Kate (2011): "Integrated online speaker clustering and adaptation", In INTERSPEECH-2011, 1085-1088.