Abstract
We present an efficient algorithm for solving the n-best-strings problem in a weighted automaton. This problem arises commonly in speech recognition applications when a ranked list of unique recognizer hypotheses is desired. We believe this is the first n-best algorithm to remove redundant hypotheses before rather than after the n-best determination. We give a detailed description of the algorithm and demonstrate its correctness. We report experimental results showing its efficiency and practicality even for large n in a 40, 000-word vocabulary North American Business News (NAB) task. In particular, we show that 1000-best generation in this task requires negligible added time over recognizer lattice generation.
| Original language | English (US) |
|---|---|
| Pages | 1313-1316 |
| Number of pages | 4 |
| State | Published - 2002 |
| Event | 7th International Conference on Spoken Language Processing, ICSLP 2002 - Denver, United States Duration: Sep 16 2002 → Sep 20 2002 |
Other
| Other | 7th International Conference on Spoken Language Processing, ICSLP 2002 |
|---|---|
| Country/Territory | United States |
| City | Denver |
| Period | 9/16/02 → 9/20/02 |
ASJC Scopus subject areas
- Language and Linguistics
- Linguistics and Language