一种用于同时语音分离和去噪的改进神经波束形成器

Zhaoheng Ni, Yong Xu, Meng Yu, Bo Wu, Shi-Xiong Zhang, Dong Yu, Michael I. Mandel
{"title":"一种用于同时语音分离和去噪的改进神经波束形成器","authors":"Zhaoheng Ni, Yong Xu, Meng Yu, Bo Wu, Shi-Xiong Zhang, Dong Yu, Michael I. Mandel","doi":"10.1109/SLT48900.2021.9383528","DOIUrl":null,"url":null,"abstract":"This paper aims at eliminating the interfering speakers' speech, additive noise, and reverberation from the noisy multi-talker speech mixture that benefits automatic speech recognition (ASR) backend. While the recently proposed Weighted Power minimization Distortionless response (WPD) beamformer can perform separation and dereverberation simultaneously, the noise cancellation component still has the potential to progress. We propose an improved neural WPD beamformer called \"WPD++\" by an enhanced beamforming module in the conventional WPD and a multi-objective loss function for the joint training. The beamforming module is improved by utilizing the spatio-temporal correlation. A multi-objective loss, including the complex spectra domain scale-invariant signal-to-noise ratio (C-Si-SNR) and the magnitude domain mean square error (Mag-MSE), is properly designed to make multiple constraints on the enhanced speech and the desired power of the dry clean signal. Joint training is conducted to optimize the complex-valued mask estimator and the WPD++ beamformer in an end-to-end way. The results show that the proposed WPD++ outperforms several state-of-the-art beamformers on the enhanced speech quality and word error rate (WER) of ASR.","PeriodicalId":243211,"journal":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"WPD++: An Improved Neural Beamformer for Simultaneous Speech Separation and Dereverberation\",\"authors\":\"Zhaoheng Ni, Yong Xu, Meng Yu, Bo Wu, Shi-Xiong Zhang, Dong Yu, Michael I. Mandel\",\"doi\":\"10.1109/SLT48900.2021.9383528\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper aims at eliminating the interfering speakers' speech, additive noise, and reverberation from the noisy multi-talker speech mixture that benefits automatic speech recognition (ASR) backend. While the recently proposed Weighted Power minimization Distortionless response (WPD) beamformer can perform separation and dereverberation simultaneously, the noise cancellation component still has the potential to progress. We propose an improved neural WPD beamformer called \\\"WPD++\\\" by an enhanced beamforming module in the conventional WPD and a multi-objective loss function for the joint training. The beamforming module is improved by utilizing the spatio-temporal correlation. A multi-objective loss, including the complex spectra domain scale-invariant signal-to-noise ratio (C-Si-SNR) and the magnitude domain mean square error (Mag-MSE), is properly designed to make multiple constraints on the enhanced speech and the desired power of the dry clean signal. Joint training is conducted to optimize the complex-valued mask estimator and the WPD++ beamformer in an end-to-end way. The results show that the proposed WPD++ outperforms several state-of-the-art beamformers on the enhanced speech quality and word error rate (WER) of ASR.\",\"PeriodicalId\":243211,\"journal\":{\"name\":\"2021 IEEE Spoken Language Technology Workshop (SLT)\",\"volume\":\"16 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-11-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE Spoken Language Technology Workshop (SLT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SLT48900.2021.9383528\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE Spoken Language Technology Workshop (SLT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SLT48900.2021.9383528","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

摘要

本文旨在消除多话音混合噪声中的干扰话音、加性噪声和混响,从而有利于自动语音识别(ASR)后端。虽然最近提出的加权最小功率无失真响应波束形成器(WPD)可以同时进行分离和去噪,但噪声消除组件仍有发展的潜力。本文提出了一种改进的WPD波束形成器“WPD++”,该波束形成器在传统WPD中增加波束形成模块,并采用多目标损失函数进行联合训练。利用时空相关性对波束形成模块进行了改进。设计了复谱域尺度不变信噪比(C-Si-SNR)和幅值域均方误差(Mag-MSE)等多目标损耗,对增强语音和干燥信号的期望功率进行了多重约束。对复值掩模估计器和WPD++波束形成器进行端到端的联合训练优化。结果表明,wpd++在增强ASR语音质量和字错误率(WER)方面优于几种最先进的波束形成器。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
WPD++: An Improved Neural Beamformer for Simultaneous Speech Separation and Dereverberation
This paper aims at eliminating the interfering speakers' speech, additive noise, and reverberation from the noisy multi-talker speech mixture that benefits automatic speech recognition (ASR) backend. While the recently proposed Weighted Power minimization Distortionless response (WPD) beamformer can perform separation and dereverberation simultaneously, the noise cancellation component still has the potential to progress. We propose an improved neural WPD beamformer called "WPD++" by an enhanced beamforming module in the conventional WPD and a multi-objective loss function for the joint training. The beamforming module is improved by utilizing the spatio-temporal correlation. A multi-objective loss, including the complex spectra domain scale-invariant signal-to-noise ratio (C-Si-SNR) and the magnitude domain mean square error (Mag-MSE), is properly designed to make multiple constraints on the enhanced speech and the desired power of the dry clean signal. Joint training is conducted to optimize the complex-valued mask estimator and the WPD++ beamformer in an end-to-end way. The results show that the proposed WPD++ outperforms several state-of-the-art beamformers on the enhanced speech quality and word error rate (WER) of ASR.
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