利用自动主题聚类改进阿拉伯语广播转录

Stephen M. Chu, L. Mangu
{"title":"利用自动主题聚类改进阿拉伯语广播转录","authors":"Stephen M. Chu, L. Mangu","doi":"10.1109/ICASSP.2012.6288907","DOIUrl":null,"url":null,"abstract":"Latent Dirichlet Allocation (LDA) has been shown to be an effective model to augment n-gram language models in speech recognition applications. In this work, we aim to take advantage of the superior unsupervised learning ability of the framework, and use it to uncover topic structure embedded in the corpora in an entirely data-driven fashion. In addition, we describe a bi-level inference and classification method that allows topic clustering at the utterance level while preserving the document-level topic structures. We demonstrate the effectiveness of the proposed topic clustering pipeline in a state-of-the-art Arabic broadcast transcription system. Experiments show that optimizing LM in the LDA topic space leads to 5% reduction in language model perplexity. It is further shown that topic clustering and adaptation is able to attain 0.4% absolute word error rate reduction on the GALE Arabic task.","PeriodicalId":6443,"journal":{"name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2012-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Improving arabic broadcast transcription using automatic topic clustering\",\"authors\":\"Stephen M. Chu, L. Mangu\",\"doi\":\"10.1109/ICASSP.2012.6288907\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Latent Dirichlet Allocation (LDA) has been shown to be an effective model to augment n-gram language models in speech recognition applications. In this work, we aim to take advantage of the superior unsupervised learning ability of the framework, and use it to uncover topic structure embedded in the corpora in an entirely data-driven fashion. In addition, we describe a bi-level inference and classification method that allows topic clustering at the utterance level while preserving the document-level topic structures. We demonstrate the effectiveness of the proposed topic clustering pipeline in a state-of-the-art Arabic broadcast transcription system. Experiments show that optimizing LM in the LDA topic space leads to 5% reduction in language model perplexity. It is further shown that topic clustering and adaptation is able to attain 0.4% absolute word error rate reduction on the GALE Arabic task.\",\"PeriodicalId\":6443,\"journal\":{\"name\":\"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2012-03-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICASSP.2012.6288907\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASSP.2012.6288907","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

摘要

在语音识别应用中,潜在狄利克雷分配(Latent Dirichlet Allocation, LDA)是一种增强n-gram语言模型的有效模型。在这项工作中,我们的目标是利用框架优越的无监督学习能力,并以完全数据驱动的方式使用它来揭示嵌入在语料库中的主题结构。此外,我们还描述了一种双级推理和分类方法,该方法允许在话语级别上进行主题聚类,同时保留文档级别的主题结构。我们在最先进的阿拉伯语广播转录系统中展示了所提出的主题聚类管道的有效性。实验表明,在LDA主题空间中优化LM可以使语言模型困惑度降低5%。进一步表明,主题聚类和自适应能够使GALE阿拉伯语任务的绝对错误率降低0.4%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Improving arabic broadcast transcription using automatic topic clustering
Latent Dirichlet Allocation (LDA) has been shown to be an effective model to augment n-gram language models in speech recognition applications. In this work, we aim to take advantage of the superior unsupervised learning ability of the framework, and use it to uncover topic structure embedded in the corpora in an entirely data-driven fashion. In addition, we describe a bi-level inference and classification method that allows topic clustering at the utterance level while preserving the document-level topic structures. We demonstrate the effectiveness of the proposed topic clustering pipeline in a state-of-the-art Arabic broadcast transcription system. Experiments show that optimizing LM in the LDA topic space leads to 5% reduction in language model perplexity. It is further shown that topic clustering and adaptation is able to attain 0.4% absolute word error rate reduction on the GALE Arabic task.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
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