Learning discriminative basis coefficients for eigenspace MLLR unsupervised adaptation

Yajie Miao, Florian Metze, A. Waibel
{"title":"Learning discriminative basis coefficients for eigenspace MLLR unsupervised adaptation","authors":"Yajie Miao, Florian Metze, A. Waibel","doi":"10.1109/ICASSP.2013.6639208","DOIUrl":null,"url":null,"abstract":"Eigenspace MLLR is effective for fast adaptation when the amount of adaptation data is limited, e.g., less than 5s. The general motivation is to represent the MLLR transform as a linear combination of basis matrices. In this paper, we present a framework to estimate a speaker-independent discriminative transform over the combination coefficients. This discriminative basis coefficients transform (DBCT) is learned by optimizing discriminative criteria over all the training speakers. During recognition, the ML basis coefficients for each testing speaker are firstly found, on which DBCT is applied to give the final MLLR transform discrimination ability. Experiments show that DBCT results in consistent WER reduction in unsupervised adaptation, compared with both standard ML and discriminatively trained transforms.","PeriodicalId":183968,"journal":{"name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","volume":"5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASSP.2013.6639208","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

Abstract

Eigenspace MLLR is effective for fast adaptation when the amount of adaptation data is limited, e.g., less than 5s. The general motivation is to represent the MLLR transform as a linear combination of basis matrices. In this paper, we present a framework to estimate a speaker-independent discriminative transform over the combination coefficients. This discriminative basis coefficients transform (DBCT) is learned by optimizing discriminative criteria over all the training speakers. During recognition, the ML basis coefficients for each testing speaker are firstly found, on which DBCT is applied to give the final MLLR transform discrimination ability. Experiments show that DBCT results in consistent WER reduction in unsupervised adaptation, compared with both standard ML and discriminatively trained transforms.
特征空间MLLR无监督自适应判别基系数的学习
在自适应数据量有限的情况下,如小于5s时,特征空间最小二乘最小二乘是有效的快速自适应。一般的动机是将MLLR变换表示为基矩阵的线性组合。在本文中,我们提出了一个估计组合系数上与说话人无关的判别变换的框架。这种判别基系数变换(DBCT)是通过优化所有训练说话者的判别标准来学习的。在识别过程中,首先找到每个测试说话人的ML基系数,在此基础上应用DBCT给出最终的MLLR变换识别能力。实验表明,与标准ML和判别训练的变换相比,DBCT在无监督自适应中产生了一致的WER降低。
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:604180095
Book学术官方微信