Structured Language Modeling for Speech Recognition

Simple item page
dc.creatorChelba, Ciprian
dc.creatorJelinek, Frederick
dc.date2000-01-25
dc.date.accessioned2026-07-07T03:15:52Z
dc.date.available2026-07-07T03:15:52Z
dc.descriptionA new language model for speech recognition is presented. The model develops hidden hierarchical syntactic-like structure incrementally and uses it to extract meaningful information from the word history, thus complementing the locality of currently used trigram models. The structured language model (SLM) and its performance in a two-pass speech recognizer --- lattice decoding --- are presented. Experiments on the WSJ corpus show an improvement in both perplexity (PPL) and word error rate (WER) over conventional trigram models.
dc.description4 pages + 2 pages of ERRATA
dc.identifierhttps://arxiv.org/abs/cs/0001023
dc.identifierhttp://arxiv.org/abs/cs/0001023
dc.identifierProceedings of NLDB'99, Klagenfurt, Austria
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/30143
dc.subjectComputation and Language
dc.subjectG.3, I.2.7, I.5.1, I.5.4
dc.titleStructured Language Modeling for Speech Recognition
dc.typetext

Files

Collections

arXiv