{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:04:28Z","timestamp":1760709868313,"version":"3.37.3"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/jstsp.2019.2908696","type":"journal-article","created":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T18:51:20Z","timestamp":1554144680000},"page":"220-235","source":"Crossref","is-referenced-by-count":6,"title":["TimeScaleNet: A Multiresolution Approach for Raw Audio Recognition Using Learnable Biquadratic IIR Filters and Residual Networks of Depthwise-Separable One-Dimensional Atrous Convolutions"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6395-634X","authenticated-orcid":false,"given":"Eric","family":"Bavu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aro","family":"Ramamonjy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hadrien","family":"Pujol","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandre","family":"Garcia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"0","journal-title":"Proc Euro Conf Comput Vision"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref33"},{"journal-title":"Digital filters and signal processing With MATLAB exercises","year":"2013","author":"jackson","key":"ref32"},{"article-title":"Tensorflow: A system for large-scale machine learning","year":"2016","author":"abadi","key":"ref31"},{"journal-title":"Discrete-Time Signal Processing","year":"2014","author":"oppenheim","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472159"},{"key":"ref36","first-page":"1945","article-title":"Batch renormalization: Towards reducing minibatch dependence in batch-normalized models","author":"ioffe","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"article-title":"Layer normalization","year":"2016","author":"ba","key":"ref34"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","first-page":"971","article-title":"Self-normalizing neural networks","author":"klambauer","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"journal-title":"Introduction to Digital Filters with Audio Applications","year":"2007","author":"smith","key":"ref29"},{"journal-title":"From Natural to Artificial Intelligence-Algorithms and Applications","year":"2018","author":"alim","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","first-page":"2067","article-title":"Gated feedback recurrent neural networks","author":"chung","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"article-title":"An efficient implementation of the Patterson–Holdsworth auditory filter bank","year":"1993","author":"slaney","key":"ref24"},{"journal-title":"Theory and Application of Digital Signal Processing","year":"1975","author":"rabiner","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178847"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.3658470"},{"article-title":"Hello edge: Keyword spotting on microcontrollers","year":"2017","author":"zhang","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462688"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00767-6_49"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/78.97998"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1459"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1121\/1.411872"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2017.8228392"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3390\/app8071152"},{"key":"ref52","first-page":"1478","article-title":"Convolutional neural networks for small-footprint keyword spotting","author":"sainath","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952585"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854950"},{"key":"ref40","first-page":"2377","article-title":"Training very deep networks","author":"greff","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952190"},{"key":"ref13","first-page":"890","article-title":"Acoustic modeling with deep neural networks using raw time signal for LVCSR","author":"t\u00fcske","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref14","first-page":"1","article-title":"Learning the speech front-end with raw waveform CLDNNS","author":"sainath","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/app8010150"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"article-title":"Wavenet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref17"},{"key":"ref18","first-page":"1","article-title":"Depthwise separable convolutions for neural machine translation","author":"kaiser","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref3","volume":"1","author":"huang","year":"2001","journal-title":"Spoken Language Processing A Guide to Theory Algorithm and System Development"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2100380"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2009.03.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2713830"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/0378-5955(90)90170-T"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-041847-6.50054-X"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","year":"2018","author":"warden","key":"ref47"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1121\/1.414456"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1515\/9783110879018.67"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/8717740\/08678740.pdf?arnumber=8678740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:08:15Z","timestamp":1657746495000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8678740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":59,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2019.2908696","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"type":"print","value":"1932-4553"},{"type":"electronic","value":"1941-0484"}],"subject":[],"published":{"date-parts":[[2019,5]]}}}