A word graph based N-best search in continuous speech recognition
- 24 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 2127-2130
- https://doi.org/10.1109/icslp.1996.607223
Abstract
The authors introduce an efficient algorithm for the exhaustive search of N-best sentence hypotheses in a word graph. The search procedure is based on a two-pass algorithm. In the first pass, a word graph is constructed with standard time-synchronous beam search. The actual extraction of N-best word sequences from the word graph takes place during the second pass. With the implementation of a tree-organized N-best list, the search is performed directly on the resulting word graph. Therefore, the parallel bookkeeping of N hypotheses at each processing step during the search is not necessary. It is important to point out that the proposed N-best search algorithm produces an exact N-best list as defined by the word graph structure. Possible errors can only result from pruning during the construction of the word graph. In a postprocessing step, the N candidates can be rescored with a more complex language model with highly reduced computational cost. This algorithm is also applied in speech understanding to select the most likely sentence hypothesis that satisfies some additional constraints.Keywords
This publication has 6 references indexed in Scilit:
- The N-best algorithms: an efficient and exact procedure for finding the N most likely sentence hypothesesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Word graphs: an efficient interface between continuous-speech recognition and language understandingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Data driven search organization for continuous speech recognitionIEEE Transactions on Signal Processing, 1992
- Improvements in beam search for 10000-word continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- A comparison of several approximate algorithms for finding multiple (N-best) sentence hypothesesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- A tree-trellis based fast search for finding the N-best sentence hypotheses in continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991