Sixth European Conference on Speech Communication and Technology

Budapest, Hungary
September 5-9, 1999

Linear Transformations in Sub-Band Groups for Speech Recognition

B. Doherty, Saeed Vaseghi, Paul McCourt

Queen’s University of Belfast, Northern Ireland, UK

Linear transforms have been demonstrated to successfully achieve on-line speaker and environmental adaptation for robust recognition. This paper explores the gains in computational speed, speaker adaptation convergence rate and recognition performance obtained through the use of multi-resolution sub-band linear transforms in speech recognition. A useful feature of multi-resolution processing is that significant savings can be attained as regards transform calculation. In this paper we appraise the relative merits of multi-band processing over that of full-band and present evaluation results on the WSJCAM0 continuous speech database.

Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Doherty, B. / Vaseghi, Saeed / McCourt, Paul (1999): "Linear transformations in sub-band groups for speech recognition", In EUROSPEECH'99, 1359-1366.