{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T01:14:00Z","timestamp":1758935640070,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746037","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"3708-3712","source":"Crossref","is-referenced-by-count":2,"title":["An Investigation of the Effectiveness of Phase for Audio Classification"],"prefix":"10.1109","author":[{"given":"Shunsuke","family":"Hidaka","sequence":"first","affiliation":[{"name":"Kyushu University,Graduate School of Design,Japan"}]},{"given":"Kohei","family":"Wakamiya","sequence":"additional","affiliation":[{"name":"Kyushu University,Faculty of Design,Japan"}]},{"given":"Tokihiko","family":"Kaburagi","sequence":"additional","affiliation":[{"name":"Kyushu University,Graduate School of Design,Japan"}]}],"member":"263","reference":[{"key":"ref33","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"ICML"},{"key":"ref32","article-title":"When does label smoothing help?","author":"m\u00fcller","year":"2019","journal-title":"NeurIPS"},{"key":"ref31","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref34","first-page":"2030","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947584"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-011-0045-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3060810"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413727"},{"year":"0","key":"ref14"},{"article-title":"librosa\/librosa: 0.8.0","year":"2020","author":"mcfee","key":"ref15"},{"key":"ref16","article-title":"LEAF: A learnable frontend for audio classification","author":"zeghidour","year":"2021","journal-title":"ICLRE"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953242"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1250\/ast.40.170"},{"key":"ref19","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"engel","year":"2017","journal-title":"ICML"},{"key":"ref28","article-title":"Deep complex networks","author":"trabelsi","year":"2018","journal-title":"ICLRE"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref27","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"ICML"},{"key":"ref3","article-title":"Acoustic scene classification in DCASE 2020 challenge: generalization across devices and low complexity solutions","author":"heittola","year":"2020","journal-title":"arXiv preprint arXiv 2005 14354"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1982.1163920"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2605"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682169"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682834"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref1","article-title":"Pushing the limits of Semi-Supervised learning for automatic speech recognition","author":"zhang","year":"2020","journal-title":"arXiv preprint arXiv 2010 10504"},{"key":"ref20","article-title":"Multiclass language identification using deep learning on spectral images of audio signals","author":"revay","year":"2019","journal-title":"arXiv preprint arXiv 1905 10797"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1111\/2041-210X.13103","article-title":"Automatic acoustic detection of birds through deep learning: The first bird audio detection challenge","volume":"10","author":"stowell","year":"2018","journal-title":"Methods Ecol Evol"},{"key":"ref21","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"arXiv preprint arXiv 1706 08612"},{"key":"ref24","article-title":"Speech commands: A dataset for Limited-Vocabulary speech recognition","author":"warden","year":"2018","journal-title":"arXiv preprint arXiv 1804 00209"},{"article-title":"TUT urban acoustic scenes 2018, development dataset","year":"2018","author":"heittola","key":"ref23"},{"key":"ref26","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746037.pdf?arnumber=9746037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:13Z","timestamp":1660594033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746037","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}