Title | ||
---|---|---|
Use Of Gaussian Selection In Large Vocabulary Continuous Speech Recognition Using Hmms |
Abstract | ||
---|---|---|
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 ken 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 x 5 reduction in likelihood computation. |
Year | DOI | Venue |
---|---|---|
1996 | 10.1109/ICSLP.1996.607156 | ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4 |
Keywords | DocType | Citations |
gaussian processes,degradation,speech recognition,decoding,hidden markov models,real time systems,dynamic range | Conference | 18 |
PageRank | References | Authors |
1.93 | 6 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kate Knill | 1 | 249 | 28.02 |
Mark J. F. Gales | 2 | 3905 | 367.45 |
Steve J. Young | 3 | 343 | 63.09 |