基于噪声自适应深度信念网络的鲁棒语音特征提取

Mohammad. Abdollahi, B. Nasersharif
{"title":"基于噪声自适应深度信念网络的鲁棒语音特征提取","authors":"Mohammad. Abdollahi, B. Nasersharif","doi":"10.1109/IRANIANCEE.2017.7985279","DOIUrl":null,"url":null,"abstract":"Deep neural networks (DNNs) have been widely used for acoustic modeling and also feature extraction in automatic speech recognition (ASR) systems. In the acoustic modeling, due to wide speaker variations, some methods have been proposed for adapting DNN to new speakers. In this paper, we propose to use this idea for adaptation of deep belief network (DBN), as a spectral feature extractor, to unknown and new noisy conditions. To this end, we use DBN in two approaches. In the first approach, we use DBN to extract logarithm of Mel sub-band energies (LMFBs) from noisy speech spectrum as robust features. In the second approach, we use DBN to estimate clean speech spectrum from the noisy one. Then, we propose to add a linear layer to DBN (as a linear adaptation method) in order to adapt DBN to unknown and new noisy conditions. This method has been applied to both mentioned DBNs. This linear layer can be added to DBN input or its output. Experimental results on Aurora2 database for ASR show that the proposed adaptation methods increase DBN performance for extracting more robust speech features. Where we have 7.5% and 11% improvement in recognition accuracy by adapting DBNs which are used as LMFB extractor and clean speech spectrum estimator, respectively.","PeriodicalId":161929,"journal":{"name":"2017 Iranian Conference on Electrical Engineering (ICEE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Noise adaptive deep belief network for robust speech features extraction\",\"authors\":\"Mohammad. Abdollahi, B. Nasersharif\",\"doi\":\"10.1109/IRANIANCEE.2017.7985279\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Deep neural networks (DNNs) have been widely used for acoustic modeling and also feature extraction in automatic speech recognition (ASR) systems. In the acoustic modeling, due to wide speaker variations, some methods have been proposed for adapting DNN to new speakers. In this paper, we propose to use this idea for adaptation of deep belief network (DBN), as a spectral feature extractor, to unknown and new noisy conditions. To this end, we use DBN in two approaches. In the first approach, we use DBN to extract logarithm of Mel sub-band energies (LMFBs) from noisy speech spectrum as robust features. In the second approach, we use DBN to estimate clean speech spectrum from the noisy one. Then, we propose to add a linear layer to DBN (as a linear adaptation method) in order to adapt DBN to unknown and new noisy conditions. This method has been applied to both mentioned DBNs. This linear layer can be added to DBN input or its output. Experimental results on Aurora2 database for ASR show that the proposed adaptation methods increase DBN performance for extracting more robust speech features. Where we have 7.5% and 11% improvement in recognition accuracy by adapting DBNs which are used as LMFB extractor and clean speech spectrum estimator, respectively.\",\"PeriodicalId\":161929,\"journal\":{\"name\":\"2017 Iranian Conference on Electrical Engineering (ICEE)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 Iranian Conference on Electrical Engineering (ICEE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IRANIANCEE.2017.7985279\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 Iranian Conference on Electrical Engineering (ICEE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IRANIANCEE.2017.7985279","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

摘要

深度神经网络(dnn)在自动语音识别(ASR)系统中广泛应用于声学建模和特征提取。在声学建模中,由于扬声器变化很大,已经提出了一些使深度神经网络适应新扬声器的方法。在本文中,我们提出将这一思想用于深度信念网络(DBN)作为一种频谱特征提取器,以适应未知和新的噪声条件。为此,我们以两种方式使用DBN。在第一种方法中,我们使用DBN从噪声语音频谱中提取Mel子带能量(lmfb)的对数作为鲁棒特征。在第二种方法中,我们使用DBN从有噪声的语音频谱中估计干净的语音频谱。然后,我们提出在DBN中添加线性层(作为线性自适应方法),以使DBN适应未知和新的噪声条件。该方法已应用于上述两个dbn。该线性层可以添加到DBN的输入或输出。在Aurora2 ASR数据库上的实验结果表明,所提出的自适应方法提高了DBN的性能,提取出更鲁棒的语音特征。其中,采用dbn分别作为LMFB提取器和干净语音频谱估计器,识别精度提高了7.5%和11%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Noise adaptive deep belief network for robust speech features extraction
Deep neural networks (DNNs) have been widely used for acoustic modeling and also feature extraction in automatic speech recognition (ASR) systems. In the acoustic modeling, due to wide speaker variations, some methods have been proposed for adapting DNN to new speakers. In this paper, we propose to use this idea for adaptation of deep belief network (DBN), as a spectral feature extractor, to unknown and new noisy conditions. To this end, we use DBN in two approaches. In the first approach, we use DBN to extract logarithm of Mel sub-band energies (LMFBs) from noisy speech spectrum as robust features. In the second approach, we use DBN to estimate clean speech spectrum from the noisy one. Then, we propose to add a linear layer to DBN (as a linear adaptation method) in order to adapt DBN to unknown and new noisy conditions. This method has been applied to both mentioned DBNs. This linear layer can be added to DBN input or its output. Experimental results on Aurora2 database for ASR show that the proposed adaptation methods increase DBN performance for extracting more robust speech features. Where we have 7.5% and 11% improvement in recognition accuracy by adapting DBNs which are used as LMFB extractor and clean speech spectrum estimator, respectively.
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