The 1995 Abbot Hybrid Connectionist-Hmm Large-Vocabulary Recognition System (original) (raw)
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. This paper describes the system which participated in the November 1995 ARPA H3 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, speci cally 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, the linear input network for speaker and environmental adaptation and the continued development of a realtime single-pass decoder well suited to the hybrid approach. Experimental results are reported for various test and development sets from the November 1994 and 1995 ARPA benchmark tests.
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.