Empirical study of neural network language models for Arabic speech recognition

Ahmad Emami, L. Mangu
{"title":"Empirical study of neural network language models for Arabic speech recognition","authors":"Ahmad Emami, L. Mangu","doi":"10.1109/ASRU.2007.4430100","DOIUrl":null,"url":null,"abstract":"In this paper we investigate the use of neural network language models for Arabic speech recognition. By using a distributed representation of words, the neural network model allows for more robust generalization and is better able to fight the data sparseness problem. We investigate different configurations of the neural probabilistic model, experimenting with such parameters as N-gram order, output vocabulary, normalization method, and model size and parameters. Experiments were carried out on Arabic broadcast news and broadcast conversations data and the optimized neural network language models showed significant improvements over the baseline N-gram model.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"52","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ASRU.2007.4430100","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 52

Abstract

In this paper we investigate the use of neural network language models for Arabic speech recognition. By using a distributed representation of words, the neural network model allows for more robust generalization and is better able to fight the data sparseness problem. We investigate different configurations of the neural probabilistic model, experimenting with such parameters as N-gram order, output vocabulary, normalization method, and model size and parameters. Experiments were carried out on Arabic broadcast news and broadcast conversations data and the optimized neural network language models showed significant improvements over the baseline N-gram model.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
神经网络语言模型在阿拉伯语语音识别中的实证研究
本文研究了神经网络语言模型在阿拉伯语语音识别中的应用。通过使用词的分布式表示,神经网络模型允许更健壮的泛化,并且能够更好地解决数据稀疏问题。我们研究了神经概率模型的不同配置,实验了N-gram顺序、输出词汇、归一化方法、模型大小和参数等参数。在阿拉伯语广播新闻和广播对话数据上进行了实验,优化后的神经网络语言模型比基线N-gram模型有了显著的改进。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Predictive linear transforms for noise robust speech recognition Development of a phonetic system for large vocabulary Arabic speech recognition Error simulation for training statistical dialogue systems An enhanced minimum classification error learning framework for balancing insertion, deletion and substitution errors Monolingual and crosslingual comparison of tandem features derived from articulatory and phone MLPS
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1