{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T01:26:41Z","timestamp":1725586001040},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T00:00:00Z","timestamp":1603238400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T00:00:00Z","timestamp":1603238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T00:00:00Z","timestamp":1603238400000},"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":[[2020,10,21]]},"DOI":"10.1109\/ictc49870.2020.9289445","type":"proceedings-article","created":{"date-parts":[[2020,12,21]],"date-time":"2020-12-21T22:58:16Z","timestamp":1608591496000},"page":"1238-1241","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Scale Multi-Band Dilated DenseLSTM for Robust Recognition of Speech with Background Music"],"prefix":"10.1109","author":[{"given":"Woon-Haeng","family":"Heo","sequence":"first","affiliation":[]},{"given":"Hyemi","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Oh-Wook","family":"Kwon","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"289","article-title":"Music source separation using stacked hourglass networks","author":"park","year":"2018","journal-title":"Proc ISMIR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8169987"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521383"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1962.sp006837"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/app10051727"},{"key":"ref15","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"Proc ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2876171"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref18","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref19","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc AISTATS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.4986931"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2354456"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107347"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ECMSM.2017.7945915"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952158"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2911401"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref9","first-page":"745","article-title":"Singing voice separation with deep U-Net convolutional networks","author":"jansson","year":"2017","journal-title":"Proc ISMIR"},{"key":"ref1","first-page":"4516","article-title":"Speech enhancement using segmental non-negative matrix factorization","author":"fan","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref20","first-page":"1508","article-title":"Multiobjective learning and mask-based post-processing for deep neural network based speech enhancement","author":"xu","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"journal-title":"Linguistic Data Consortium","article-title":"CSR-II (WSJ1) Complete","year":"1994","key":"ref24"},{"article-title":"The MUSDB18 corpus for music separation","year":"2017","author":"rafii","key":"ref23"},{"key":"ref26","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"}],"event":{"name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","start":{"date-parts":[[2020,10,21]]},"location":"Jeju, Korea (South)","end":{"date-parts":[[2020,10,23]]}},"container-title":["2020 International Conference on Information and Communication Technology Convergence (ICTC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9289075\/9289076\/09289445.pdf?arnumber=9289445","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:12:20Z","timestamp":1656375140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9289445\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,21]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ictc49870.2020.9289445","relation":{},"subject":[],"published":{"date-parts":[[2020,10,21]]}}}