4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Use of Gaussian Selection in Large Vocabulary Continuous Speech Recognition Using HMMs

K. M. Knill, M. J. F. Gales, S. J. Young

Cambridge University Engineering Department, Cambridge, UK

This paper investigates the use of Gaussian Selection (GS) to reduce the state likelihood computation in HMM-based systems. These likelihood calculations contribute significantly (30 to 70%) to the computational load. Previously, it has been reported that when GS is used on large systems the recognition accuracy tends to degrade above a x3 reduction in likelihood computation. To explain this degradation, this paper investigates the trade-offs necessary between achieving good state likelihoods and low computation. In addition, the problem of unseen states in a cluster is examined. It is shown that further improvements are possible. For example, using a different assignment measure, with a constraint on the number of components per state per cluster, enabled the recognition accuracy on a 5k speaker-independent task to be maintained up to a x5 reduction in likelihood computation.

Full Paper

Bibliographic reference.  Knill, K. M. / Gales, M. J. F. / Young, S. J. (1996): "Use of Gaussian selection in large vocabulary continuous speech recognition using HMMs", In ICSLP-1996, 470-473.