Abstract
This paper presents a detailed comparison between two search optimization techniques for large vocabulary speech recognition - one based on word-conditioned tree search (WCTS) and one based on weighted finite-state transducers (WFSTs). Existing North American Business News systems from RWTH and AT&T representing each of the two approaches, were modified to remove variations in model data and acoustic likelihood computation. An experimental comparison showed that the WFST-based system explored fewer search states and had less runtime overhead than the WCTS-based system for a given word error rate. This is attributed to differences in the pre-compilation, degree of non-determinism, and path weight distribution in the respective search graphs.
| Original language | English (US) |
|---|---|
| Pages | 1309-1312 |
| 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