Title :
A comparison of several approximate algorithms for finding multiple (N-best) sentence hypotheses
Author :
Schwartz, Richard ; Austin, Steve
Author_Institution :
BBN Syst. & Technol., Cambridge, MA, USA
Abstract :
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
Keywords :
approximation theory; search problems; speech recognition; Viterbi scoring; error rate; exact sentence-dependent method; lattice N-best method; multiple sentence hypotheses; recognition accuracy; total likelihood scoring; word-dependent N-best algorithm; Hidden Markov models; Laser sintering; Lattices; Natural languages; Neutron spin echo; Sorting; Stochastic systems;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on
Conference_Location :
Toronto, Ont.
Print_ISBN :
0-7803-0003-3
DOI :
10.1109/ICASSP.1991.150436