{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:35:30Z","timestamp":1730230530030,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","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":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682378","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"5686-5690","source":"Crossref","is-referenced-by-count":2,"title":["Timescalenet : A Multiresolution Approach for Raw Audio Recognition"],"prefix":"10.1109","author":[{"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":[{"journal-title":"Theory and Application of Digital Signal Processing","year":"1975","author":"rabiner","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178847"},{"key":"ref12","article-title":"An efficient implementation of the Patterson-Holdsworth auditory filter bank","volume":"35","author":"slaney","year":"1993","journal-title":"Apple Computer Perception Group Tech Rep"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.3658470"},{"journal-title":"Introduction to Digital Filters with Audio Applications","year":"2007","author":"smith","key":"ref14"},{"article-title":"Layer normalization","year":"2016","author":"ba","key":"ref15"},{"key":"ref16","first-page":"971","article-title":"Self-normalizing neural networks","author":"klambauer","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1515\/9783110879018.67"},{"key":"ref4","article-title":"Learning the speech front-end with raw waveform CLDNNs","author":"sainath","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"article-title":"Acoustic modeling with deep neural networks using raw time signal for LVCSR","year":"0","author":"t\u00fcske","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/app8010150"},{"key":"ref8","article-title":"Depthwise separable convolutions for neural machine translation","author":"kaiser","year":"2018","journal-title":"International Conference on Learning Representations"},{"article-title":"Wavenet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952190"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854950"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","year":"2018","author":"warden","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462688"},{"article-title":"Hello edge: Keyword spotting on mi-crocontrollers","year":"2017","author":"zhang","key":"ref21"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682378.pdf?arnumber=8682378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:14:55Z","timestamp":1657854895000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682378\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682378","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}