{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:06:56Z","timestamp":1740100016768,"version":"3.37.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414018","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"101-105","source":"Crossref","is-referenced-by-count":1,"title":["Capturing Temporal Dependencies Through Future Prediction for CNN-Based Audio Classifiers"],"prefix":"10.1109","author":[{"given":"Hongwei","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiqing","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiwen","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"141","article-title":"Transfer learning for music classification and regression tasks","author":"choi","year":"2017","journal-title":"Proc ISMIR"},{"article-title":"Environmental sound classification with parallel temporal-spectral attention","year":"2019","author":"wang","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2975422"},{"key":"ref14","article-title":"Learning from between-class examples for deep sound recognition","author":"tokozume","year":"2018","journal-title":"Proc ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/app8010150"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"article-title":"Contrastive predictive coding based feature for automatic speaker verification","year":"2019","author":"lai","key":"ref17"},{"article-title":"Layer normalization","year":"2016","author":"ba","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683288"},{"key":"ref4","first-page":"1159","article-title":"Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription","author":"boulanger-lewandowski","year":"2012","journal-title":"Proc ICML"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"oord","key":"ref5"},{"article-title":"Rethinking cnn models for audio classification","year":"2020","author":"palanisamy","key":"ref8"},{"article-title":"Esresnet: Environmental sound classification based on visual domain models","year":"2020","author":"guzhov","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2016.12.024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref22","article-title":"Superconvergence: Very fast training of residual networks using large learning rates","author":"smith","year":"2017","journal-title":"CoRR"},{"article-title":"Decoupled weight decay regularization","year":"0","author":"loshchilov","key":"ref21"},{"key":"ref24","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017","journal-title":"NIPS 2017 Workshop on Autodiff"},{"key":"ref23","first-page":"4694","article-title":"When does label smoothing help?","author":"m\u00fcller","year":"2019","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414018.pdf?arnumber=9414018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:07Z","timestamp":1652197267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414018","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}