.png){kind=icon}
返回
Continuous space language models
.png){kind=icon}
PRE
AI
DOI：10.1016/j.csl.2006.09.003.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper describes the use of a neural network language model for large vocabulary continuous speech recognition. The underlying idea of this approach is to attack the data sparseness problem by performing the language model probability estimation in a continuous space. Highly efficient learning algorithms are described that enable the use of training corpora of several hundred million words. It is also shown that this approach can be incorporated into a large vocabulary continuous speech recognizer using a lattice rescoring framework at a very low additional processing time. The neural network language model was thoroughly evaluated in a state-of-the-art large vocabulary continuous speech recognizer for several international benchmark tasks, in particular the NIST evaluations on broadcast news and conversational speech recognition. The new approach is compared to four-gram back-off language models trained with modified Kneser-Ney smoothing which has often been reported to be the best known smoothing method. Usually the neural network language model is interpolated with the back-off language model. In that way, consistent word error rate reductions for all considered tasks and languages were achieved, ranging from 0.4% to almost 1% absolute. (c) 2006 Elsevier Ltd. All rights reserved.
Keyword:
MAXIMUM-ENTROPY APPROACH
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
C
IF:
3.4
论文数:
1.5K
被引数:
2.6K
机构
暂无机构信息
引用论文
.png){kind=icon}
Using Micro-Simulation VISSIM to Study the Effectiveness of Left-Turn Waiting Area Implementation
PREAI
分享收藏The rearrangement and simple cleavage of metastable octanamine radical cations不稳定辛胺自由基阳离子的重排与简单断裂
PREAI
分享收藏
查看更多内容