The 1994 HTK large vocabulary speech recognition system
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 73-76
- https://doi.org/10.1109/icassp.1995.479276
Abstract
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 65 k 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.Keywords
This publication has 5 references indexed in Scilit:
- Large vocabulary continuous speech recognition using HTKPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Large vocabulary continuous speech recognition of Wall Street Journal dataPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- A one pass decoder design for large vocabulary recognitionPublished by Association for Computational Linguistics (ACL) ,1994
- Tree-based state tying for high accuracy acoustic modellingPublished by Association for Computational Linguistics (ACL) ,1994
- Estimation of probabilities from sparse data for the language model component of a speech recognizerIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987