Speech Enhancement Based on Multi-Objective Ensemble Learning

Yonglin Wu, Jun Zhang, Yue Wu, Geng-xin Ning, Cui Yang
{"title":"Speech Enhancement Based on Multi-Objective Ensemble Learning","authors":"Yonglin Wu, Jun Zhang, Yue Wu, Geng-xin Ning, Cui Yang","doi":"10.1109/ICSPCC55723.2022.9984412","DOIUrl":null,"url":null,"abstract":"The performance of traditional speech enhancement methods based on deep neural network is limited by using single training objective and network structure. In this paper, we propose a speech enhancement method based on multi-objective ensemble learning. First, the traditional multi-objective learning network structure is modified to reduce the training conflict caused by excess shared parameters. Then, a multi-objective ensemble learning based speech enhancement method is established by employing the modified multi-objective deep neural network (DNN), convolutional neural network (CNN) and gate recurrent unit (GRU), which overcomes the limitation of homogeneity in base models in the traditional ensemble learning based speech enhancement network. The experimental results show that the proposed methods outperforms the traditional multi-objective learning or ensemble learning based speech enhancement methods at the scores of perceptual evaluation of speech quality (PESQ) and short-time objective intelligibility (STOI).","PeriodicalId":346917,"journal":{"name":"2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSPCC55723.2022.9984412","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

The performance of traditional speech enhancement methods based on deep neural network is limited by using single training objective and network structure. In this paper, we propose a speech enhancement method based on multi-objective ensemble learning. First, the traditional multi-objective learning network structure is modified to reduce the training conflict caused by excess shared parameters. Then, a multi-objective ensemble learning based speech enhancement method is established by employing the modified multi-objective deep neural network (DNN), convolutional neural network (CNN) and gate recurrent unit (GRU), which overcomes the limitation of homogeneity in base models in the traditional ensemble learning based speech enhancement network. The experimental results show that the proposed methods outperforms the traditional multi-objective learning or ensemble learning based speech enhancement methods at the scores of perceptual evaluation of speech quality (PESQ) and short-time objective intelligibility (STOI).
基于多目标集成学习的语音增强
传统的基于深度神经网络的语音增强方法受单一训练目标和网络结构的限制。本文提出了一种基于多目标集成学习的语音增强方法。首先,对传统的多目标学习网络结构进行改进,减少共享参数过多导致的训练冲突;然后,采用改进的多目标深度神经网络(DNN)、卷积神经网络(CNN)和门递归单元(GRU),建立了一种基于多目标集成学习的语音增强方法,克服了传统基于集成学习的语音增强网络中基模型同质性的局限性。实验结果表明,所提方法在语音质量感知评价(PESQ)和短时客观可理解度(STOI)得分上优于传统的多目标学习或基于集成学习的语音增强方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
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