{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:35:00Z","timestamp":1767339300264,"version":"3.37.3"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1109\/iscas51556.2021.9401593","type":"proceedings-article","created":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T21:33:36Z","timestamp":1619559216000},"page":"1-5","source":"Crossref","is-referenced-by-count":12,"title":["Learnable MFCCs for Speaker Verification"],"prefix":"10.1109","author":[{"given":"Xuechen","family":"Liu","sequence":"first","affiliation":[]},{"given":"Md","family":"Sahidullah","sequence":"additional","affiliation":[]},{"given":"Tomi","family":"Kinnunen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref31","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017","journal-title":"NIPS 2017 Workshop on Autodiff"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"},{"article-title":"Melnet: A generative model for audio in the frequency domain","year":"2019","author":"vasquez","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053038"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2191960"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1140"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2326991"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/97.928676"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758101"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2545928"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CSPC.2017.8305805"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1129"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref3","first-page":"4052","article-title":"Deep neural networks for small footprint text-dependent speaker verification","author":"variani","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015 San Diego CA USA May 7-9 2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2264"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462015"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1765"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1978.10837"},{"key":"ref21","first-page":"249","article-title":"Understanding the difficulty of training deep feed-forward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"journal-title":"Fundamentals of speech recognition","year":"1993","author":"lawrence","key":"ref24"},{"journal-title":"Matrix Computations","year":"1996","author":"golub","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-3"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-21606-5","author":"hastie","year":"2001","journal-title":"The Elements of Statistical Learning"}],"event":{"name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","start":{"date-parts":[[2021,5,22]]},"location":"Daegu, Korea","end":{"date-parts":[[2021,5,28]]}},"container-title":["2021 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9401028\/9401051\/09401593.pdf?arnumber=9401593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:44:12Z","timestamp":1652197452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9401593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iscas51556.2021.9401593","relation":{},"subject":[],"published":{"date-parts":[[2021,5]]}}}