Proceedings ICASSP'95, Detroit, 1995
The 1994 HTK Large Vocabulary Speech Recognition System
P.C. Woodland, C.J. Leggetter, J.J. Odell, V. Valtchev and S.J. Young

This paper describes recent work on the HTK large vocabulary speech recognition system. The system uses tied-state cross-word context- dependent mixture Gaussian HMMs and a dynamic network decoder that can operate in a single pass. In the last year the decoder has been extended to produce word lattices to allow flexible and efficient system development, as well as multi-pass operation for use with computationally expensive acoustic and/or language models. The system vocabulary can now be up to 65k words, the final acoustic models have been extended to be sensitive to more acoustic context (quinphones), a 4-gram language model has been used and unsupervised incremental speaker adaptation incorporated. The resulting system gave the lowest error rates on both the H1-P0 and H1-C1 hub tasks in the November 1994 ARPA CSR evaluation.

compress'd PS