A comparison of several approximate algorithms for finding multiple (N-best) sentence hypotheses

The authors introduce a new, more efficient algorithm, the word-dependent N-best algorithm, for finding multiple sentence hypotheses. The proposed algorithm is based on the assumption that the beginning time of a word depends only on the preceding word. The authors compare this algorithm with two other algorithms for finding the N-best hypotheses: the exact sentence-dependent method and a computationally efficient lattice N-best method. Although the word-dependent algorithm is computationally much less expensive than the exact algorithm, it appears to result in the same accuracy. The lattice method, which is still more efficient, has a significantly higher error rate. It is demonstrated that algorithms that use Viterbi scoring have significantly higher error rates than those that use total likelihood scoring.<<ETX>>

[1]  Hy Murveit,et al.  Integrating natural language constraints into HMM-based speech recognition , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[2]  Volker Steinbiss,et al.  Sentence-hypotheses generation in a continuous-speech recognition system , 1989, EUROSPEECH.

[3]  José B. Mariño,et al.  Generation of multiple hypothesis in connected phonetic-unit recognition by a modified one-stage dynamic programming algorithm , 1989, EUROSPEECH.

[4]  Patti Price,et al.  The DARPA 1000-word resource management database for continuous speech recognition , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[5]  John Makhoul,et al.  Context-dependent modeling for acoustic-phonetic recognition of continuous speech , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  Y.-L. Chow.  Maximum mutual information estimation of HMM parameters for continuous speech recognition using the N-best algorithm , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[7]  Richard M. Schwartz,et al.  Continuous speech recognition using segmental neural nets , 1991 .

[8]  R. Schwartz,et al.  The N-best algorithms: an efficient and exact procedure for finding the N most likely sentence hypotheses , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[9]  Mari Ostendorf,et al.  Integration of Diverse Recognition Methodologies Through Reevaluation of N-Best Sentence Hypotheses , 1991, HLT.

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