目的评价双音过程中残余回波抑制的指标

Amir Ivry, I. Cohen, B. Berdugo
{"title":"目的评价双音过程中残余回波抑制的指标","authors":"Amir Ivry, I. Cohen, B. Berdugo","doi":"10.1109/WASPAA52581.2021.9632787","DOIUrl":null,"url":null,"abstract":"Human subjective evaluation is optimal to assess speech quality for human perception. The recently introduced deep noise suppression mean opinion score (DNSMOS) metric was shown to estimate human ratings with great accuracy. The signal-to-distortion ratio (SDR) metric is widely used to evaluate residual-echo suppression (RES) systems by estimating speech quality during double-talk. However, since the SDR is affected by both speech distortion and residual-echo presence, it does not correlate well with human ratings according to the DNSMOS. To address that, we introduce two objective metrics to separately quantify the desired-speech maintained level (DSML) and residual-echo suppression level (RESL) during double-talk. These metrics are evaluated using a deep learning-based RES-system with a tunable design parameter. Using 280 hours of real and simulated recordings, we show that the DSML and RESL correlate well with the DNSMOS with high generalization to various setups. Also, we empirically investigate the relation between tuning the RES-system design parameter and the DSML-RESL tradeoff it creates and offer a practical design scheme for dynamic system requirements.","PeriodicalId":429900,"journal":{"name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Objective Metrics to Evaluate Residual-Echo Suppression During Double-Talk\",\"authors\":\"Amir Ivry, I. Cohen, B. Berdugo\",\"doi\":\"10.1109/WASPAA52581.2021.9632787\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Human subjective evaluation is optimal to assess speech quality for human perception. The recently introduced deep noise suppression mean opinion score (DNSMOS) metric was shown to estimate human ratings with great accuracy. The signal-to-distortion ratio (SDR) metric is widely used to evaluate residual-echo suppression (RES) systems by estimating speech quality during double-talk. However, since the SDR is affected by both speech distortion and residual-echo presence, it does not correlate well with human ratings according to the DNSMOS. To address that, we introduce two objective metrics to separately quantify the desired-speech maintained level (DSML) and residual-echo suppression level (RESL) during double-talk. These metrics are evaluated using a deep learning-based RES-system with a tunable design parameter. Using 280 hours of real and simulated recordings, we show that the DSML and RESL correlate well with the DNSMOS with high generalization to various setups. Also, we empirically investigate the relation between tuning the RES-system design parameter and the DSML-RESL tradeoff it creates and offer a practical design scheme for dynamic system requirements.\",\"PeriodicalId\":429900,\"journal\":{\"name\":\"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)\",\"volume\":\"2016 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-07-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/WASPAA52581.2021.9632787\",\"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 Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WASPAA52581.2021.9632787","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

人类的主观评价是评价人类感知语音质量的最佳方法。最近引入的深度噪声抑制平均意见评分(DNSMOS)度量被证明可以非常准确地估计人类的评分。信号失真比(SDR)度量被广泛用于评估残留回波抑制(RES)系统,通过估计双讲时的语音质量。然而,由于SDR受到语音失真和残余回波存在的影响,因此根据DNSMOS,它与人类评级的相关性并不好。为了解决这个问题,我们引入了两个客观指标来分别量化双语期间的期望语音维持水平(DSML)和残余回波抑制水平(RESL)。这些指标使用基于深度学习的res系统进行评估,该系统具有可调的设计参数。使用280小时的真实和模拟记录,我们表明DSML和RESL与DNSMOS具有良好的相关性,对各种设置具有很高的泛化性。此外,我们还实证研究了调整res系统设计参数与DSML-RESL权衡之间的关系,并为动态系统需求提供了一个实用的设计方案。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Objective Metrics to Evaluate Residual-Echo Suppression During Double-Talk
Human subjective evaluation is optimal to assess speech quality for human perception. The recently introduced deep noise suppression mean opinion score (DNSMOS) metric was shown to estimate human ratings with great accuracy. The signal-to-distortion ratio (SDR) metric is widely used to evaluate residual-echo suppression (RES) systems by estimating speech quality during double-talk. However, since the SDR is affected by both speech distortion and residual-echo presence, it does not correlate well with human ratings according to the DNSMOS. To address that, we introduce two objective metrics to separately quantify the desired-speech maintained level (DSML) and residual-echo suppression level (RESL) during double-talk. These metrics are evaluated using a deep learning-based RES-system with a tunable design parameter. Using 280 hours of real and simulated recordings, we show that the DSML and RESL correlate well with the DNSMOS with high generalization to various setups. Also, we empirically investigate the relation between tuning the RES-system design parameter and the DSML-RESL tradeoff it creates and offer a practical design scheme for dynamic system requirements.
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:604180095
Book学术官方微信