The key problem to be faced when building a HMM-based continuous speech recogniser is maintaining the balance between model complexity and available training data. For large vocabulary systems requiring crossword context dependent modelling, this is particularly acute since many mmh contexts will never occur in the training data. This paper describes a method of creating a tied-state continuous speech recognition system using a phonetic decision tree. This treebased clustering is shown to lead to similar recognition performance to that obtained using an earlier data-driven approach but to have the additional advantage of providing a mapping for unseen triphones. State-tying is also compared with traditional model-based tying and shown to be clearly superior. Experimental results are presented for both the Resource Management and Wall Street 3ournal tasks.

No abstract

No abstract

No abstract