Comparison of Various Neural Network Language Models in Speech Recognition

Lingyun Zuo, Jian Liu, Xin Wan
{"title":"Comparison of Various Neural Network Language Models in Speech Recognition","authors":"Lingyun Zuo, Jian Liu, Xin Wan","doi":"10.1109/ICISCE.2016.195","DOIUrl":null,"url":null,"abstract":"In recent years, research on language modeling for speech recognition has increasingly focused on the application of neural networks. However, the performance of neural network language models strongly depends on their architectural structure. Three competing concepts have been developed: Firstly, feed forward neural networks representing an n-gram approach, Secondly, recurrent neural networks that may learn context dependencies spanning more than a fixed number of predecessor words, Thirdly, the long short-term memory (LSTM) neural networks can fully exploits the correlation on a telephone conversation corpus. In this paper, we compare count models to feed forward, recurrent, and LSTM neural network in conversational telephone speech recognition tasks. Furthermore, we put forward a language model estimation method introduced the information of history sentences. We evaluate the models in terms of perplexity and word error rate, experimentally validating the strong correlation of the two quantities, which we find to hold regardless of the underlying type of the language model. The experimental results show that the performance of LSTM neural network language model is optimal in n-best lists re-score. Compared to the first pass decoding, the relative decline in average word error rate is 4.3% when using ten candidate results to re-score in conversational telephone speech recognition tasks.","PeriodicalId":6882,"journal":{"name":"2016 3rd International Conference on Information Science and Control Engineering (ICISCE)","volume":"35 1","pages":"894-898"},"PeriodicalIF":0.0000,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 3rd International Conference on Information Science and Control Engineering (ICISCE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICISCE.2016.195","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

In recent years, research on language modeling for speech recognition has increasingly focused on the application of neural networks. However, the performance of neural network language models strongly depends on their architectural structure. Three competing concepts have been developed: Firstly, feed forward neural networks representing an n-gram approach, Secondly, recurrent neural networks that may learn context dependencies spanning more than a fixed number of predecessor words, Thirdly, the long short-term memory (LSTM) neural networks can fully exploits the correlation on a telephone conversation corpus. In this paper, we compare count models to feed forward, recurrent, and LSTM neural network in conversational telephone speech recognition tasks. Furthermore, we put forward a language model estimation method introduced the information of history sentences. We evaluate the models in terms of perplexity and word error rate, experimentally validating the strong correlation of the two quantities, which we find to hold regardless of the underlying type of the language model. The experimental results show that the performance of LSTM neural network language model is optimal in n-best lists re-score. Compared to the first pass decoding, the relative decline in average word error rate is 4.3% when using ten candidate results to re-score in conversational telephone speech recognition tasks.
各种神经网络语言模型在语音识别中的比较
近年来,针对语音识别的语言建模研究越来越关注神经网络的应用。然而,神经网络语言模型的性能在很大程度上取决于其体系结构。三个相互竞争的概念已经发展起来:首先,前馈神经网络代表了一种n-gram方法;其次,循环神经网络可以学习超过固定数量的前馈词的上下文依赖关系;第三,长短期记忆(LSTM)神经网络可以充分利用电话会话语料库上的相关性。在本文中,我们比较了计数模型与前馈、循环和LSTM神经网络在会话电话语音识别任务中的应用。在此基础上,提出了一种引入历史句子信息的语言模型估计方法。我们根据困惑和单词错误率来评估模型,通过实验验证了这两个量的强相关性,我们发现无论语言模型的底层类型如何,这两个量都具有很强的相关性。实验结果表明,LSTM神经网络语言模型在n个最优列表重新评分时性能最优。与第一次解码相比,在会话电话语音识别任务中使用10个候选结果重新评分时,平均单词错误率的相对下降幅度为4.3%。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信