The BBN single-phonetic-tree fast-match algorithm

In this paper 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 fastmatch, 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. 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]  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.

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

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

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

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

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

[7]  Richard M. Schwartz,et al.  Search Algorithms for Software-Only Real-Time Recognition with Very Large Vocabularies , 1993, HLT.