Large vocabulary word recognition based on tree-trellis search
- 17 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. ii (15206149) , II/137-II/140
- https://doi.org/10.1109/icassp.1994.389700
Abstract
In this paper we propose a large vocabulary (90000 words), Chinese (Mandarin) word recognizer based on the tree-trellis fast search algorithm. The recognizer is divided into 3 modules: local likelihood computation, a forward trellis search and a backward tree search. In the forward trellis search, a free syllable decoding is performed without a language model and a partial path map is created. The best-first tree search is then applied backward along a lexicon, which is arranged as a syllabic tree, to find the N-best word candidates. In the experiment, context-dependent subsyllabic HMMs were trained with a new discriminative training method. When it is evaluated on a speaker-trained database, the recognizer achieved a word error rate of 5% for the full size (90000 words) vocabulary and 1.7% for a smaller subset (5000 words) vocabulary. A real-time demo system has also been implemented on an SGI R-4000 workstation.<>Keywords
This publication has 5 references indexed in Scilit:
- An N-best candidates-based discriminative training for speech recognition applicationsIEEE Transactions on Speech and Audio Processing, 1994
- A look-ahead search technique for large vocabulary continuous speech recognitionPublished by International Speech Communication Association ,1991
- A tree-trellis based fast search for finding the N-best sentence hypotheses in continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Fast search strategy in a large vocabulary word recognizerThe Journal of the Acoustical Society of America, 1988
- Principles of Artificial IntelligencePublished by Springer Nature ,1982