Name
Title | ||
|---|---|---|
Spontaneous dialogue speech recognition using cross-word context constrained word graphs |
Abstract | ||
|---|---|---|
This paper proposes a large vocabulary spontaneous dialogue speech recognizer using cross-word context constrained word graphs. In this method, two approximation methods “cross-word context approximation” and “lenient language score smearing” are introduced to reduce the computational cost for word graph generation. The experimental results using a “travel arrangement corpus” show that this recognition method achieves a word hypotheses reduction of 25-40% and a cpu-time reduction of 30-60% compared to without approximation, and that the use of class bigram scores as the expected language score for each lexicon tree node decreases the word error rate 25-30% compared to without approximation |
Year | DOI | Venue |
|---|---|---|
1996 | 10.1109/ICASSP.1996.540311 | Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference |
Keywords | Field | DocType |
approximation theory,context-sensitive grammars,interactive systems,natural languages,speech recognition,CPU time reduction,approximation methods,class bigram scores,computational cost reduction,cross-word context approximation,cross-word context constrained word graphs,expected language score,experimental results,large vocabulary spontaneous dialogue recognizer,lenient language score smearing,lexicon tree node,spontaneous dialogue speech recognition,travel arrangement corpus,word error rate,word graph generation,word hypotheses reduction | Tree (graph theory),Computer science,Natural language processing,Bigram,Artificial intelligence,Graph,Pattern recognition,Word error rate,Approximation theory,Speech recognition,Natural language,Lexicon,Vocabulary | Conference |
Volume | ISSN | ISBN |
1 | 1520-6149 | 0-7803-3192-3 |
Citations | PageRank | References |
41 | 7.71 | 8 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shimizu, T. | 1 | 41 | 7.71 |
| Yamamoto, H. | 2 | 81 | 20.20 |
| Masataki, H. | 3 | 41 | 7.71 |
| Matsunaga, S. | 4 | 477 | 49.70 |