多任务自编码器与Wasserstein生成对抗网络相结合,提高语音识别性能

IF 0.2 Q4 ACOUSTICS
C. Kao, Hanseok Ko
{"title":"多任务自编码器与Wasserstein生成对抗网络相结合,提高语音识别性能","authors":"C. Kao, Hanseok Ko","doi":"10.7776/ASK.2019.38.6.670","DOIUrl":null,"url":null,"abstract":"As the presence of background noise in acoustic signal degrades the performance of speech or acoustic event recognition, it is still challenging to extract noise-robust acoustic features from noisy signal. In this paper, we propose a combined structure of Wasserstein Generative Adversarial Network (WGAN) and MultiTask AutoEncoder (MTAE) as deep learning architecture that integrates the strength of MTAE and WGAN respectively such that it estimates not only noise but also speech features from noisy acoustic source. The proposed MTAE-WGAN structure is used to estimate speech signal and the residual noise by employing a gradient penalty and a weight initialization method for Leaky Rectified Linear Unit (LReLU) and Parametric ReLU (PReLU). The proposed MTAE-WGAN structure with the adopted gradient penalty loss function enhances the speech features and subsequently achieve substantial Phoneme Error Rate (PER) improvements over the stand-alone Deep Denoising Autoencoder (DDAE), MTAE, Redundant Convolutional Encoder-Decoder (R-CED) and Recurrent MTAE (RMTAE) models for robust speech recognition.","PeriodicalId":42689,"journal":{"name":"Journal of the Acoustical Society of Korea","volume":null,"pages":null},"PeriodicalIF":0.2000,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Combining multi-task autoencoder with Wasserstein generative adversarial networks for improving speech recognition performance\",\"authors\":\"C. Kao, Hanseok Ko\",\"doi\":\"10.7776/ASK.2019.38.6.670\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"As the presence of background noise in acoustic signal degrades the performance of speech or acoustic event recognition, it is still challenging to extract noise-robust acoustic features from noisy signal. In this paper, we propose a combined structure of Wasserstein Generative Adversarial Network (WGAN) and MultiTask AutoEncoder (MTAE) as deep learning architecture that integrates the strength of MTAE and WGAN respectively such that it estimates not only noise but also speech features from noisy acoustic source. The proposed MTAE-WGAN structure is used to estimate speech signal and the residual noise by employing a gradient penalty and a weight initialization method for Leaky Rectified Linear Unit (LReLU) and Parametric ReLU (PReLU). The proposed MTAE-WGAN structure with the adopted gradient penalty loss function enhances the speech features and subsequently achieve substantial Phoneme Error Rate (PER) improvements over the stand-alone Deep Denoising Autoencoder (DDAE), MTAE, Redundant Convolutional Encoder-Decoder (R-CED) and Recurrent MTAE (RMTAE) models for robust speech recognition.\",\"PeriodicalId\":42689,\"journal\":{\"name\":\"Journal of the Acoustical Society of Korea\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.2000,\"publicationDate\":\"2019-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of the Acoustical Society of Korea\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.7776/ASK.2019.38.6.670\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ACOUSTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the Acoustical Society of Korea","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.7776/ASK.2019.38.6.670","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ACOUSTICS","Score":null,"Total":0}
引用次数: 0

摘要

由于声学信号中背景噪声的存在降低了语音或声学事件识别的性能,因此从噪声信号中提取噪声鲁棒的声学特征仍然具有挑战性。在本文中,我们提出了一种Wasserstein生成对抗性网络(WGAN)和多任务自动编码器(MTAE)的组合结构作为深度学习架构,该结构分别集成了MTAE和WGAN的强度,使其不仅可以估计噪声,还可以从噪声声源中估计语音特征。所提出的MTAE-WGAN结构通过对泄漏整流线性单元(LReLU)和参数ReLU(PReLU)采用梯度惩罚和权重初始化方法来估计语音信号和残余噪声。与用于鲁棒语音识别的独立深度去噪自动编码器(DDAE)、MTAE、冗余卷积编码器-解码器(R-CED)和递归MTAE(RMTAE)模型相比,所提出的具有所采用的梯度惩罚损失函数的MTAE-WGAN结构增强了语音特征,并随后实现了显著的语音误码率(PER)改进。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Combining multi-task autoencoder with Wasserstein generative adversarial networks for improving speech recognition performance
As the presence of background noise in acoustic signal degrades the performance of speech or acoustic event recognition, it is still challenging to extract noise-robust acoustic features from noisy signal. In this paper, we propose a combined structure of Wasserstein Generative Adversarial Network (WGAN) and MultiTask AutoEncoder (MTAE) as deep learning architecture that integrates the strength of MTAE and WGAN respectively such that it estimates not only noise but also speech features from noisy acoustic source. The proposed MTAE-WGAN structure is used to estimate speech signal and the residual noise by employing a gradient penalty and a weight initialization method for Leaky Rectified Linear Unit (LReLU) and Parametric ReLU (PReLU). The proposed MTAE-WGAN structure with the adopted gradient penalty loss function enhances the speech features and subsequently achieve substantial Phoneme Error Rate (PER) improvements over the stand-alone Deep Denoising Autoencoder (DDAE), MTAE, Redundant Convolutional Encoder-Decoder (R-CED) and Recurrent MTAE (RMTAE) models for robust speech recognition.
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
CiteScore
0.60
自引率
50.00%
发文量
1
×
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