Improvements in beam search for 10000-word continuous speech recognition
- 1 January 1992
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 9-12 vol.1
- https://doi.org/10.1109/icassp.1992.225985
Abstract
The author describes the improvements in a time synchronous beam search strategy for a 10000-word continuous speech recognition task. The improvements are based on two measures: a tree-organization of the pronunciation lexicon and a novel look-ahead technique at the phoneme level, both of which interact directly with the detailed search at the state levels of the phoneme models. Experimental tests were performed for four speakers on a 12306-word task. As a result of the above measures, the overall search effort was reduced by a factor of 17 without a loss in recognition accuracy.Keywords
This publication has 6 references indexed in Scilit:
- A data-driven organization of the dynamic programming beam search for continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Continuous-speech recognition using a stochastic language modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Experiments on mixture-density phoneme-modelling for the speaker-independent 1000-word speech recognition DARPA taskPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A fast approximate acoustic match for large vocabulary speech recognitionIEEE Transactions on Speech and Audio Processing, 1993
- Recognition of Words in Very Large VocabularyPublished by Springer Nature ,1988
- The CASPERS linguistic analysis systemIEEE Transactions on Acoustics, Speech, and Signal Processing, 1975