论文信息 - A*-admissible heuristics for rapid lexical access

A*-admissible heuristics for rapid lexical access

The authors present a new class of A* algorithms for Viterbi phonetic decoding subject to lexical constraints. They show that this type of algorithm can be made to run substantially faster than the Viterbi algorithm in an isolated word recognizer having a vocabulary of 1600 words and that it runs very quickly on a 60000-word recognition task. In addition, multiple recognition hypotheses can be generated on demand and the search can be constrained to respect conditions on phone durations in such a way that computational requirements are substantially reduced.<<ETX>>

[1] Richard M. Schwartz,et al. The N-Best Algorithm: Efficient Procedure for Finding Top N Sentence Hypotheses , 1989, HLT.

[2] F. Jelinek,et al. Continuous speech recognition by statistical methods , 1976, Proceedings of the IEEE.

[3] Frank K. Soong. A phonetically labeled acoustic segment (PLAS) approach to speech analysis-synthesis , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[4] Frank K. Soong,et al. A Tree.Trellis Based Fast Search for Finding the N Best Sentence Hypotheses in Continuous Speech Recognition , 1990, HLT.

[5] D. O'Shaughnessy,et al. Using phoneme duration and energy contour information to improve large vocabulary isolated-word recognition , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[6] John E. Hopcroft,et al. An n log n algorithm for minimizing states in a finite automaton , 1971 .

[7] Stephen E. Levinson,et al. Continuous speech recognition from a phonetic transcription , 1990, International Conference on Acoustics, Speech, and Signal Processing.