4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

The 1995 Abbot LVCSR System for Multiple Unknown Microphones

Dan Kershaw (1), Tony Robinson (1), Steve Renals (2)

(1) Cambridge University Engineering Department, Cambridge, UK
(2) Department of Computer Science, Sheffield, UK

ABBOT is the hybrid connectionist-hidden Markov model large-vocabulary speech recognition system developed at Cambridge University. In this system, a recurrent network maps each acoustic vector to an estimate of the posterior probabilities of the phone classes, which are used as observation probabilities within an HMM. This paper describes the system which participated in the November 1995 ARPA Hub-3 Multiple Unknown Microphones (MUM) evaluation of continuous speech recognition systems, under the guise of the CU-CON system. The emphasis of the paper is on the changes made to the 1994 ABBOT system, specifically to accomodate the H3 task. This includes improved acoustic modelling using limited word-internal context-dependent models, training on the Wall Street Journal secondary channel database, and using the linear input network for speaker and environmental adaptation. Experimental results are reported for various test and development sets from the November 1994 and 1995 ARPA benchmark tests.

Full Paper

Bibliographic reference.  Kershaw, Dan / Robinson, Tony / Renals, Steve (1996): "The 1995 abbot LVCSR system for multiple unknown microphones", In ICSLP-1996, 1325-1328.