Efficient WFST-Based One-Pass Decoding With On-The-Fly Hypothesis Rescoring in Extremely Large Vocabulary Continuous Speech Recognition
Authors:
- Takaaki HoriTHTakaaki Hori
- Chiori HoriCHChiori Hori
- Yasuhiro MinamiYMYasuhiro Minami
- Atsushi NakamuraANAtsushi Nakamura
- 23 April 2007
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 15 (4) , 1352-1365
Abstract
This paper proposes a novel one-pass search algorithm with on-the-fly composition of weighted finite-state transducers (WFSTs) for large-vocabulary continuous-speech recognition. In the standard search method with on-the-fly composition, two or more WFSTs are composed during decoding, and a Viterbi search is performed based on the composed search space. With this new method, a Viterbi search is performed based on the first of the two WFSTs. The second WFST is only used to rescore the hypotheses generated during the search. Since this rescoring is very efficient, the total amount of computation required by the new method is almost the same as when using only the first WFST. In a 65k-word vocabulary spontaneous lecture speech transcription task, our proposed method significantly outperformed the standard search method. Furthermore, our method was faster than decoding with a single fully composed and optimized WFST, where our method used only 38% of the memory required for decoding with the single WFST. Finally, we have achieved high-accuracy one-pass real-time speech recognition with an extremely large vocabulary of 1.8 million wordsKeywords
This publication has 10 references indexed in Scilit:
- Finite-state transducers for speech-input translation2005
- A tail-sharing WFST composition algorithm for large vocabulary speech recognition2003
- Deriving disambiguous queries in a spoken interactive ODQA system2003
- Spontaneous dialogue speech recognition using cross-word context constrained word graphs2002
- Minimizing search errors due to delayed bigrams in real-time speech recognition systems2002
- Efficient support vector classifiers for named entity recognition2002
- Weighted finite-state transducers in speech recognitionComputer Speech & Language, 2002
- A word graph algorithm for large vocabulary continuous speech recognitionComputer Speech & Language, 1997
- Vector quantization for the efficient computation of continuous density likelihoods1993
- A comparison of several approximate algorithms for finding multiple (N-best) sentence hypotheses1991