Sciweavers

Share
NAACL
1994

A One Pass Decoder Design For Large Vocabulary Recognition

10 years 2 months ago
A One Pass Decoder Design For Large Vocabulary Recognition
To achieve reasonable accuracy in large vocabulary speech recognition systems, it is important to use detailed acoustic models together with good long span language models. For example, in the Wall Street Journal (WSJ) task both cross-word triphones and a trigram language model are necessary to achieve state-of-the-art performance. However, when using these models, the size of a pre-compiled recognition network can make a standard Viterbi search infeasible and hence, either multiple-pass or asynchronous stack decoding schemes are typically used. In tl:fispaper, we show that timesynchronous one-pass decoding using cross-word triphones and a trigram language model can be implemented using a dynamically built tree-structured network. This approach avoids the compromises inherent in using fast-matches or preliminary passes and is relatively efficient in implementation. It was included in the HTK large vocabulary speech recognition system used for the 1993 ARPA WSJ evaluation and experimen...
J. J. Odell, V. Valtchev, Philip C. Woodland, S. J
Added 02 Nov 2010
Updated 02 Nov 2010
Type Conference
Year 1994
Where NAACL
Authors J. J. Odell, V. Valtchev, Philip C. Woodland, S. J. Young
Comments (0)
books