使用神经离散时频表示学习的条件声音生成

Xubo Liu, Turab Iqbal, Jinzheng Zhao, Qiushi Huang, Mark D. Plumbley, Wenwu Wang
{"title":"使用神经离散时频表示学习的条件声音生成","authors":"Xubo Liu, Turab Iqbal, Jinzheng Zhao, Qiushi Huang, Mark D. Plumbley, Wenwu Wang","doi":"10.1109/mlsp52302.2021.9596430","DOIUrl":null,"url":null,"abstract":"Deep generative models have recently achieved impressive performance in speech and music synthesis. However, compared to the generation of those domain-specific sounds, generating general sounds (such as siren, gunshots) has received less attention, despite their wide applications. In previous work, the SampleRNN method was considered for sound generation in the time domain. However, SampleRNN is potentially limited in capturing long-range dependencies within sounds as it only back-propagates through a limited number of samples. In this work, we propose a method for generating sounds via neural discrete time-frequency representation learning, conditioned on sound classes. This offers an advantage in efficiently modelling long-range dependencies and retaining local fine-grained structures within sound clips. We evaluate our approach on the UrbanSound8K dataset, compared to SampleRNN, with the performance metrics measuring the quality and diversity of generated sounds. Experimental results show that our method offers comparable performance in quality and significantly better performance in diversity.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"32","resultStr":"{\"title\":\"Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning\",\"authors\":\"Xubo Liu, Turab Iqbal, Jinzheng Zhao, Qiushi Huang, Mark D. Plumbley, Wenwu Wang\",\"doi\":\"10.1109/mlsp52302.2021.9596430\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Deep generative models have recently achieved impressive performance in speech and music synthesis. However, compared to the generation of those domain-specific sounds, generating general sounds (such as siren, gunshots) has received less attention, despite their wide applications. In previous work, the SampleRNN method was considered for sound generation in the time domain. However, SampleRNN is potentially limited in capturing long-range dependencies within sounds as it only back-propagates through a limited number of samples. In this work, we propose a method for generating sounds via neural discrete time-frequency representation learning, conditioned on sound classes. This offers an advantage in efficiently modelling long-range dependencies and retaining local fine-grained structures within sound clips. We evaluate our approach on the UrbanSound8K dataset, compared to SampleRNN, with the performance metrics measuring the quality and diversity of generated sounds. Experimental results show that our method offers comparable performance in quality and significantly better performance in diversity.\",\"PeriodicalId\":156116,\"journal\":{\"name\":\"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)\",\"volume\":\"28 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-07-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"32\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/mlsp52302.2021.9596430\",\"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 31st International Workshop on Machine Learning for Signal Processing (MLSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/mlsp52302.2021.9596430","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 32

摘要

深度生成模型最近在语音和音乐合成方面取得了令人印象深刻的表现。然而,与产生那些特定领域的声音相比,产生一般声音(如警笛,枪声)受到的关注较少,尽管它们被广泛应用。在以前的工作中,SampleRNN方法被考虑用于时域的声音生成。然而,SampleRNN在捕获声音中的远程依赖关系方面可能受到限制,因为它只能通过有限数量的样本进行反向传播。在这项工作中,我们提出了一种通过以声音类别为条件的神经离散时频表示学习来生成声音的方法。这在有效地建模远程依赖关系和保留声音片段中的局部细粒度结构方面提供了优势。与SampleRNN相比,我们在UrbanSound8K数据集上评估了我们的方法,并使用性能指标衡量生成声音的质量和多样性。实验结果表明,该方法在质量上具有相当的性能,在多样性上具有明显的优势。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning
Deep generative models have recently achieved impressive performance in speech and music synthesis. However, compared to the generation of those domain-specific sounds, generating general sounds (such as siren, gunshots) has received less attention, despite their wide applications. In previous work, the SampleRNN method was considered for sound generation in the time domain. However, SampleRNN is potentially limited in capturing long-range dependencies within sounds as it only back-propagates through a limited number of samples. In this work, we propose a method for generating sounds via neural discrete time-frequency representation learning, conditioned on sound classes. This offers an advantage in efficiently modelling long-range dependencies and retaining local fine-grained structures within sound clips. We evaluate our approach on the UrbanSound8K dataset, compared to SampleRNN, with the performance metrics measuring the quality and diversity of generated sounds. Experimental results show that our method offers comparable performance in quality and significantly better performance in diversity.
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