Problem-Solving Methods in Artificial Intelligence
Problem-Solving Methods in Artificial Intelligence
Recent progress on the VOYAGER system
HLT '90 Proceedings of the workshop on Speech and Natural Language
Benchmark tests for the DARPA Spoken Language Program
HLT '93 Proceedings of the workshop on Human Language Technology
| Hi-index | 0.01 |
In this paper, we propose a search algorithm that incrementally makes effective use of detailed sources of knowledge. The proposed algorithm incrementally applies all available acoustic and linguistic infomation in three search phases. Phase one is a left to right Viterbi beam search that produces word end times and scores using right context between-word models with a bigram language model. Phase two, guided by results from phase one, is a right to left Viterbi beam search that produces word begin times and scores based on left context between-word models. Phase three is an A* search that combines the results of phases one and two with a long distance language model. Our objective is to maximize the recognition accuracy with a minimal increase in computational cost. With our decomposed, incremental, search algorithm, we show that early use of detailed acoustic models can significantly reduce the recognition error rate with a negligible increase in computational cost.