Large vocabulary continuous speech recognition of Wall Street Journal data
- 1 January 1993
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (15206149) , 640-643 vol.2
- https://doi.org/10.1109/icassp.1993.319391
Abstract
The authors report on the progress that has been made at Dragon Systems in speaker-independent large-vocabulary speech recognition using speech from DARPA's Wall Street Journal corpus. First they present an overview of the recognition and training algorithms. Then, they describe experiments involving two improvements to these algorithms, moving to higher-dimensional streams and using an IMELDA transformation. They also present some results showing the reduction in error rates.Keywords
This publication has 10 references indexed in Scilit:
- Tied mixture continuous parameter models for large vocabulary isolated speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Rapid match training for large vocabulariesPublished by Association for Computational Linguistics (ACL) ,1992
- The design for the wall street journal-based CSR corpusPublished by Association for Computational Linguistics (ACL) ,1992
- Large vocabulary recognition of Wall Street Journal sentences at Dragon SystemsPublished by Association for Computational Linguistics (ACL) ,1992
- Dragon systems resource management benchmark results---February 1991Published by Association for Computational Linguistics (ACL) ,1991
- An investigation of PLP and IMELDA acoustic representations and of their potential for combinationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- A rapid match algorithm for continuous speech recognitionPublished by Association for Computational Linguistics (ACL) ,1990
- Phoneme-in-context modeling for dragon's continuous speech recognizerPublished by Association for Computational Linguistics (ACL) ,1990
- The dragon continuous speech recognition systemPublished by Association for Computational Linguistics (ACL) ,1990
- Large-vocabulary speaker-independent continuous speech recognition with semi-continuous hidden Markov modelsPublished by Association for Computational Linguistics (ACL) ,1989