Recognition Performance of a Structured Language Model
| dc.creator | Chelba, Ciprian | |
| dc.creator | Jelinek, Frederick | |
| dc.date | 2000-01-24 | |
| dc.date.accessioned | 2026-07-07T03:15:52Z | |
| dc.date.available | 2026-07-07T03:15:52Z | |
| dc.description | A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history - thus enabling the use of extended distance dependencies - in an attempt to complement the locality of currently used trigram models. The structured language model, its probabilistic parameterization and performance in a two-pass speech recognizer are presented. Experiments on the SWITCHBOARD corpus show an improvement in both perplexity and word error rate over conventional trigram models. | |
| dc.description | 4 pages | |
| dc.identifier | https://arxiv.org/abs/cs/0001022 | |
| dc.identifier | http://arxiv.org/abs/cs/0001022 | |
| dc.identifier | Proceedings of Eurospeech, 1999, pp. 1567-1570, Budapest, Hungary | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/30142 | |
| dc.subject | Computation and Language | |
| dc.subject | G.3, I.2.7, I.5.1, I.5.4 | |
| dc.title | Recognition Performance of a Structured Language Model | |
| dc.type | text |