TadaStride:在音频数据中使用时间自适应步长,实现有效降采样

IF 3.1 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Computer Speech and Language Pub Date : 2024-06-10 DOI:10.1016/j.csl.2024.101678
Yoonhyung Lee , Kyomin Jung
{"title":"TadaStride:在音频数据中使用时间自适应步长,实现有效降采样","authors":"Yoonhyung Lee ,&nbsp;Kyomin Jung","doi":"10.1016/j.csl.2024.101678","DOIUrl":null,"url":null,"abstract":"<div><p>In this paper, we introduce a new downsampling method for audio data called TadaStride, which can adaptively adjust the downsampling ratios across an audio data instance. Unlike previous methods using a fixed downsampling ratio, TadaStride can preserve more information from task-relevant parts of a data instance by using smaller strides for those parts and larger strides for less relevant parts. Additionally, we also introduce TadaStride-F, which is developed as a more efficient version of TadaStride while maintaining minimal performance loss. In experiments, we evaluate our TadaStride, primarily focusing on a range of audio processing tasks. Firstly, in audio classification experiments, TadaStride and TadaStride-F outperform other widely used standard downsampling methods, even with comparable memory and time usage. Furthermore, through various analyses, we provide an understanding of how TadaStride learns effective adaptive strides and how it leads to improved performance. In addition, through additional experiments on automatic speech recognition and discrete speech representation learning, we demonstrate that TadaStride and TadaStride-F consistently outperform other downsampling methods and examine how the adaptive strides are learned in these tasks.</p></div>","PeriodicalId":50638,"journal":{"name":"Computer Speech and Language","volume":"89 ","pages":"Article 101678"},"PeriodicalIF":3.1000,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0885230824000615/pdfft?md5=5861e2f1cdebf31ffd61d0cba92056f3&pid=1-s2.0-S0885230824000615-main.pdf","citationCount":"0","resultStr":"{\"title\":\"TadaStride: Using time adaptive strides in audio data for effective downsampling\",\"authors\":\"Yoonhyung Lee ,&nbsp;Kyomin Jung\",\"doi\":\"10.1016/j.csl.2024.101678\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>In this paper, we introduce a new downsampling method for audio data called TadaStride, which can adaptively adjust the downsampling ratios across an audio data instance. Unlike previous methods using a fixed downsampling ratio, TadaStride can preserve more information from task-relevant parts of a data instance by using smaller strides for those parts and larger strides for less relevant parts. Additionally, we also introduce TadaStride-F, which is developed as a more efficient version of TadaStride while maintaining minimal performance loss. In experiments, we evaluate our TadaStride, primarily focusing on a range of audio processing tasks. Firstly, in audio classification experiments, TadaStride and TadaStride-F outperform other widely used standard downsampling methods, even with comparable memory and time usage. Furthermore, through various analyses, we provide an understanding of how TadaStride learns effective adaptive strides and how it leads to improved performance. In addition, through additional experiments on automatic speech recognition and discrete speech representation learning, we demonstrate that TadaStride and TadaStride-F consistently outperform other downsampling methods and examine how the adaptive strides are learned in these tasks.</p></div>\",\"PeriodicalId\":50638,\"journal\":{\"name\":\"Computer Speech and Language\",\"volume\":\"89 \",\"pages\":\"Article 101678\"},\"PeriodicalIF\":3.1000,\"publicationDate\":\"2024-06-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S0885230824000615/pdfft?md5=5861e2f1cdebf31ffd61d0cba92056f3&pid=1-s2.0-S0885230824000615-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer Speech and Language\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0885230824000615\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Speech and Language","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0885230824000615","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

本文介绍了一种新的音频数据降采样方法 TadaStride,它可以自适应地调整音频数据实例的降采样比例。与以往使用固定下采样率的方法不同,TadaStride 可以通过对数据实例中与任务相关的部分使用较小的步长,而对不太相关的部分使用较大的步长,从而保留这些部分的更多信息。此外,我们还引入了 TadaStride-F,它是 TadaStride 的更高效版本,同时性能损失最小。在实验中,我们主要针对一系列音频处理任务对 TadaStride 进行了评估。首先,在音频分类实验中,TadaStride 和 TadaStride-F 优于其他广泛使用的标准降采样方法,即使内存和时间使用量相当。此外,通过各种分析,我们了解了 TadaStride 如何学习有效的自适应步长,以及如何提高性能。此外,通过在自动语音识别和离散语音表征学习方面的其他实验,我们证明了 TadaStride 和 TadaStride-F 始终优于其他降采样方法,并研究了在这些任务中如何学习自适应步长。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
TadaStride: Using time adaptive strides in audio data for effective downsampling

In this paper, we introduce a new downsampling method for audio data called TadaStride, which can adaptively adjust the downsampling ratios across an audio data instance. Unlike previous methods using a fixed downsampling ratio, TadaStride can preserve more information from task-relevant parts of a data instance by using smaller strides for those parts and larger strides for less relevant parts. Additionally, we also introduce TadaStride-F, which is developed as a more efficient version of TadaStride while maintaining minimal performance loss. In experiments, we evaluate our TadaStride, primarily focusing on a range of audio processing tasks. Firstly, in audio classification experiments, TadaStride and TadaStride-F outperform other widely used standard downsampling methods, even with comparable memory and time usage. Furthermore, through various analyses, we provide an understanding of how TadaStride learns effective adaptive strides and how it leads to improved performance. In addition, through additional experiments on automatic speech recognition and discrete speech representation learning, we demonstrate that TadaStride and TadaStride-F consistently outperform other downsampling methods and examine how the adaptive strides are learned in these tasks.

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
Computer Speech and Language
Computer Speech and Language 工程技术-计算机:人工智能
CiteScore
11.30
自引率
4.70%
发文量
80
审稿时长
22.9 weeks
期刊介绍: Computer Speech & Language publishes reports of original research related to the recognition, understanding, production, coding and mining of speech and language. The speech and language sciences have a long history, but it is only relatively recently that large-scale implementation of and experimentation with complex models of speech and language processing has become feasible. Such research is often carried out somewhat separately by practitioners of artificial intelligence, computer science, electronic engineering, information retrieval, linguistics, phonetics, or psychology.
期刊最新文献
Modeling correlated causal-effect structure with a hypergraph for document-level event causality identification You Are What You Write: Author re-identification privacy attacks in the era of pre-trained language models End-to-End Speech-to-Text Translation: A Survey TR-Net: Token Relation Inspired Table Filling Network for Joint Entity and Relation Extraction Refining the evaluation of speech synthesis: A summary of the Blizzard Challenge 2023
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1