Structured Language Modeling for Speech Recognition
计算与语言
2007-05-23 v1
摘要
A 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.
引用
@article{arxiv.cs/0001023,
title = {Structured Language Modeling for Speech Recognition},
author = {Ciprian Chelba and Frederick Jelinek},
journal= {arXiv preprint arXiv:cs/0001023},
year = {2007}
}
备注
4 pages + 2 pages of ERRATA