{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:47:57Z","timestamp":1781016477750,"version":"3.54.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Department of Atomic Energy","award":["DAE\/34\/20\/12\/2018-BRNS\/34088"],"award-info":[{"award-number":["DAE\/34\/20\/12\/2018-BRNS\/34088"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.3030489","type":"journal-article","created":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T19:40:46Z","timestamp":1602704446000},"page":"2823-2836","source":"Crossref","is-referenced-by-count":19,"title":["Interpretable Representation Learning for Speech and Audio Signals Based on Relevance Weighting"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1165-8348","authenticated-orcid":false,"given":"Purvi","family":"Agrawal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5779-9066","authenticated-orcid":false,"given":"Sriram","family":"Ganapathy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858055"},{"key":"ref38","first-page":"1","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref33","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":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-805"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1121\/1.5001926"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760373"},{"key":"ref37","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"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/nn831"},{"key":"ref34","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"arXiv 1607 08022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857801"},{"key":"ref27","first-page":"1607","article-title":"Data-driven design of RASTA-like filters","volume":"1","author":"vuuren","year":"0","journal-title":"Proc EUROSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2913965"},{"key":"ref2","first-page":"1","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.1998.0281"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.181"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref24","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"shazeer","year":"2017","journal-title":"ICLRE"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953204"},{"key":"ref50","first-page":"1566","article-title":"Voices obscured in complex environmental settings (VOiCES) corpus","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1837"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1794"},{"key":"ref54","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"arXiv 1703 03130"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952190"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682520"},{"key":"ref40","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1972"},{"key":"ref14","first-page":"1","article-title":"Interpretable convolutional filters with SincNet","author":"ravanelli","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/asi.4630270302"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/258525.258529"},{"key":"ref17","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0000909"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/jocn_a_01245"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707746"},{"key":"ref3","first-page":"1766","article-title":"Estimating phoneme class conditional probabilities from raw speech signal using convolutional neural networks","author":"palaz","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178847"},{"key":"ref5","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 INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472808"},{"key":"ref7","first-page":"1","article-title":"Learning the speech front-end with raw waveform CLDNNs","author":"sainath","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2652"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/89.326616"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288820"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326009"},{"key":"ref47","first-page":"1696","article-title":"Mean Hilbert envelope coefficients (MHEC) for robust speaker recognition","author":"sadjadi","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.4405-12.2013"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1121\/1.2816572"},{"key":"ref44","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref43","article-title":"PyTorch","volume":"1","author":"paszke","year":"2017","journal-title":"Computer software Vers 0 3"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09224148.pdf?arnumber=9224148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:23Z","timestamp":1651080683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9224148\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.3030489","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}