基于自动学习稀疏逆协方差矩阵的低资源语音识别

Weibin Zhang, Pascale Fung
{"title":"基于自动学习稀疏逆协方差矩阵的低资源语音识别","authors":"Weibin Zhang, Pascale Fung","doi":"10.1109/ICASSP.2012.6288977","DOIUrl":null,"url":null,"abstract":"Full covariance acoustic models trained with limited training data generalize poorly to unseen test data due to a large number of free parameters. We propose to use sparse inverse covariance matrices to address this problem. Previous sparse inverse covariance methods never outperformed full covariance methods. We propose a method to automatically drive the structure of inverse covariance matrices to sparse during training. We use a new objective function by adding L1 regularization to the traditional objective function for maximum likelihood estimation. The graphic lasso method for the estimation of a sparse inverse covariance matrix is incorporated into the Expectation Maximization algorithm to learn parameters of HMM using the new objective function. Experimental results show that we only need about 25% of the parameters of the inverse covariance matrices to be nonzero in order to achieve the same performance of a full covariance system. Our proposed system using sparse inverse covariance Gaussians also significantly outperforms a system using full covariance Gaussians trained on limited data.","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":"4","resultStr":"{\"title\":\"Lowresource speech recognition with automatically learned sparse inverse covariance matrices\",\"authors\":\"Weibin Zhang, Pascale Fung\",\"doi\":\"10.1109/ICASSP.2012.6288977\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Full covariance acoustic models trained with limited training data generalize poorly to unseen test data due to a large number of free parameters. We propose to use sparse inverse covariance matrices to address this problem. Previous sparse inverse covariance methods never outperformed full covariance methods. We propose a method to automatically drive the structure of inverse covariance matrices to sparse during training. We use a new objective function by adding L1 regularization to the traditional objective function for maximum likelihood estimation. The graphic lasso method for the estimation of a sparse inverse covariance matrix is incorporated into the Expectation Maximization algorithm to learn parameters of HMM using the new objective function. Experimental results show that we only need about 25% of the parameters of the inverse covariance matrices to be nonzero in order to achieve the same performance of a full covariance system. Our proposed system using sparse inverse covariance Gaussians also significantly outperforms a system using full covariance Gaussians trained on limited data.\",\"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\":\"4\",\"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.2012.6288977\",\"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.2012.6288977","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

摘要

用有限的训练数据训练的全协方差声学模型由于有大量的自由参数,对未知的测试数据泛化效果较差。我们建议使用稀疏逆协方差矩阵来解决这个问题。以往的稀疏反协方差方法的性能从未优于全协方差方法。提出了一种在训练过程中自动将逆协方差矩阵的结构驱动为稀疏的方法。在最大似然估计的传统目标函数基础上加入L1正则化,提出了一种新的目标函数。将稀疏逆协方差矩阵的图形lasso估计方法与期望最大化算法相结合,利用新的目标函数学习HMM的参数。实验结果表明,我们只需要约25%的逆协方差矩阵参数为非零,就能达到与全协方差系统相同的性能。我们提出的使用稀疏逆协方差高斯的系统也显著优于在有限数据上训练的使用全协方差高斯的系统。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Lowresource speech recognition with automatically learned sparse inverse covariance matrices
Full covariance acoustic models trained with limited training data generalize poorly to unseen test data due to a large number of free parameters. We propose to use sparse inverse covariance matrices to address this problem. Previous sparse inverse covariance methods never outperformed full covariance methods. We propose a method to automatically drive the structure of inverse covariance matrices to sparse during training. We use a new objective function by adding L1 regularization to the traditional objective function for maximum likelihood estimation. The graphic lasso method for the estimation of a sparse inverse covariance matrix is incorporated into the Expectation Maximization algorithm to learn parameters of HMM using the new objective function. Experimental results show that we only need about 25% of the parameters of the inverse covariance matrices to be nonzero in order to achieve the same performance of a full covariance system. Our proposed system using sparse inverse covariance Gaussians also significantly outperforms a system using full covariance Gaussians trained on limited data.
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