Recent Improvements To The Abbot Large Vocabulary Csr System (1995)
| Citations: | 13 - 7 self |
BibTeX
@MISC{Renals95recentimprovements,
author = {Hochberg Renals and M. M. Hochberg and S. J. Renals and A. J. Robinson and G. D. Cook},
title = {Recent Improvements To The Abbot Large Vocabulary Csr System},
year = {1995}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
ABBOT is the hybrid connectionist-hidden Markov model (HMM) large-vocabulary continuous speech recognition (CSR) system developed at Cambridge University. This system uses a recurrent network to estimate the acoustic observation probabilities within an HMM framework. A major advantage of this approach is that good performance is achieved using context-independent acoustic models and requiring many fewer parameters than comparable HMM systems. This paper presents substantial performance improvements gained from new approaches to connectionist model combination and phone-duration modeling. Additional capability has also been achieved by extending the decoder to handle larger vocabulary tasks (20,000 words and greater) with a trigram language model. This paper describes the recent modifications to the system and experimental results are reported for various test and development sets from the November 1992, 1993, and 1994 ARPA evaluations of spoken language systems. 1. INTRODUCTION This p...
Citations
| 976 | An algorithm for vector quantizer design - Linde, Buzo, et al. - 1980 |
| 368 | Connectionist Speech Recognition: A Hybrid Approach - Bourlard, Morgan - 1993 |
| 165 | An application to recurrent nets to phone probability estimation - Robinson - 1994 |
| 132 | The Design for the Wall Street Journal-based CSR Corpus - Paul, Baker - 1992 |
| 46 | Large vocabulary continuous speech recognition using HTK - Woodland, Odell, et al. - 1994 |
| 30 | Efficient Search Using Posterior Phone Probability Estimates - Renals, Hochberg - 1995 |
| 12 | Large Vocabulary Continuous Speech Recognition Using a Hybrid Connectionist-HMM System - Hochberg, Renals, et al. - 1994 |
| 10 | Learning phonological rule probabilities from speech corpora with Exploratory Computational Phonology," 33rd Annual Meeting of the Association for Computational Linguistics - Tajchman, Jurafsky, et al. - 1995 |
| 3 | Methods and experiments for text-indepedent speaker recognition over telephone channels - Gish, Kransner, et al. - 1986 |
