Performance of the IBM large vocabulary continuous speech recognition system on the ARPA Wall Street Journal task
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 41-44 vol.1
- https://doi.org/10.1109/icassp.1995.479268
Abstract
In this paper we discuss various experimental results using our continuous speech recognition system on the Wall Street Journal task. Experiments with different feature extraction methods, varying amounts and type of training data, and different vocabulary sizes are reported.Keywords
This publication has 8 references indexed in Scilit:
- Robust methods for using context-dependent features and models in a continuous speech recognizerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Improving speech recognition performance via phone-dependent VQ codebooks and adaptive language models in SPHINX-IIPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Large vocabulary continuous speech recognition using HTKPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Genones: optimizing the degree of mixture tying in a large vocabulary hidden Markov model based speech recognizerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The LIMSI continuous speech dictation system: evaluation on the ARPA Wall Street Journal taskPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Comparative experiments on large vocabulary speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- 1993 benchmark tests for the ARPA spoken language programPublished by Association for Computational Linguistics (ACL) ,1994
- Context dependent vector quantization for continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993