The development of the 1994 HTK large vocabulary speech recognition system

This paper describes recent developments of the HTK large vocabulary continuous speech recognition system. The system uses tied-state crossword 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 exible and eecient 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 nal 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.