Recognition Performance of a Structured Language Model
计算与语言
2007-05-23 v1
摘要
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.
引用
@article{arxiv.cs/0001022,
title = {Recognition Performance of a Structured Language Model},
author = {Ciprian Chelba and Frederick Jelinek},
journal= {arXiv preprint arXiv:cs/0001022},
year = {2007}
}
备注
4 pages