Toward a real-time spoken language system using commercial hardware
HLT '90 Proceedings of the workshop on Speech and Natural Language
A simple statistical class grammar for measuring speech recognition performance
HLT '89 Proceedings of the workshop on Speech and Natural Language
The N-Best algorithm: an efficient procedure for finding top N sentence hypotheses
HLT '89 Proceedings of the workshop on Speech and Natural Language
BYBLOS speech recognition benchmark results
HLT '91 Proceedings of the workshop on Speech and Natural Language
Integration of diverse recognition methodologies through reevaluation of N-best sentence hypotheses
HLT '91 Proceedings of the workshop on Speech and Natural Language
Toward a real-time spoken language system using commercial hardware
HLT '90 Proceedings of the workshop on Speech and Natural Language
BBN BYBLOS and HARC February 1992 ATIS benchmark results
HLT '91 Proceedings of the workshop on Speech and Natural Language
BBN real-time speech recognition demonstrations
HLT '91 Proceedings of the workshop on Speech and Natural Language
Weight estimation for N-best rescoring
HLT '91 Proceedings of the workshop on Speech and Natural Language
Search algorithms for software-only real-time recognition with very large vocabularies
HLT '93 Proceedings of the workshop on Human Language Technology
A one pass decoder design for large vocabulary recognition
HLT '94 Proceedings of the workshop on Human Language Technology
Efficient backward decoding of high-order hidden Markov models
Pattern Recognition
An utterance verification algorithm in keyword spotting system
IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part II
| Hi-index | 0.00 |
We present two efficient search algorithms for real-time spoken language systems. The first called the Word-Dependent N-Best algorithm is an improved algorithm for finding the top N sentence hypotheses. The new algorithm is shown to perform as well as the Exact Sentence-Dependent algorithm presented previously but with an order of magnitude less computation. The second algorithm is a fast match scheme for continuous speech recognition called the Forward-Backward Search. This algorithm, which is directly motivated by the Baum-Welch Forward-Backward training algorithm, has been shown to reduce the computation of a time-synchronous beam search by a factor of 40 with no additional search errors.