Single-tree method for grammar-directed search

We present a very fast and accurate fast-match algorithm which, when followed by a regular beam search restricted within only the subset of words selected by the fast-match, can speed up the recognition process by at least two orders of magnitude in comparison to a typical single-pass speech recognizer utilizing the Viterbi (or beam) search algorithm. In this search strategy, the recognition vocabulary is structured as a single phonetic tree in the fast-match pass. The search on this phonetic tree is a variation of the Viterbi algorithm. Especially, we are able to use a word bigram language model without making copies of the tree during the search. This is a novel fast-match algorithm that has two important properties: high-accuracy recognition and run-time proportional to only the cube root of the vocabulary size.

[1]  R. Schwartz,et al.  Single tree method for grammar directed, very large vocabulary speech recognizer , 1997 .

[2]  Long Nguyen,et al.  Multiple-Pass Search Strategies , 1996 .

[3]  Steve Austin,et al.  The forward-backward search algorithm , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[4]  Richard M. Schwartz,et al.  Towards a robust real-time decoder , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[5]  Bruce T. Lowerre,et al.  The HARPY speech recognition system , 1976 .

[6]  George Zavaliagkos,et al.  Is N-Best Dead? , 1994, HLT.

[7]  H. Ney,et al.  Improvements in beam search for 10000-word continuous speech recognition , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  Richard M. Schwartz,et al.  Efficient 2-pass n-best decoder , 1997, EUROSPEECH.