{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:03:11Z","timestamp":1730304191181,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"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":[[2023,10,22]]},"DOI":"10.1109\/waspaa58266.2023.10248164","type":"proceedings-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T17:31:37Z","timestamp":1694799097000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["A Novel Method to Detect Instrumental Music in a Large Scale Music Catalog"],"prefix":"10.1109","author":[{"given":"Wo Jae","family":"Lee","sequence":"first","affiliation":[{"name":"Amazon Music"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuele","family":"Coviello","sequence":"additional","affiliation":[{"name":"Amazon Music"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-210"},{"article-title":"SpeechBrain: A general-purpose speech toolkit","year":"2021","author":"ravanelli","key":"ref12"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2182510"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/e24010114"},{"article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"howard","key":"ref31"},{"article-title":"Adam: A method for stochastic optimization. arxiv prepr. int","year":"2014","author":"diederik","key":"ref30"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2825108"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-268"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref32"},{"journal-title":"Yamnet","year":"0","key":"ref2"},{"article-title":"musicnn: Pre-trained convolutional neural networks for music audio tagging","year":"2019","author":"pons","key":"ref1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177944"},{"key":"ref16","first-page":"1","article-title":"Separation of a monaural audio signal into harmonic\/percussive components by complementary diffusion on spectrogram","author":"ono","year":"2008","journal-title":"2008 16th European Signal Processing Conference"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2381716.2381722"},{"key":"ref18","first-page":"121","article-title":"Exploring data augmentation for improved singing voice detection with neural networks","author":"schl\u00fcter","year":"2015","journal-title":"ISMIR"},{"article-title":"Gsep: A robust vocal and accompaniment separation system using gated cbhg module and loudness normalization","year":"2020","author":"park","key":"ref24"},{"key":"ref23","first-page":"3","article-title":"Deep learning based music source separation","volume":"1","author":"henning","year":"2021","journal-title":"SCSU Journal of Student Scholarship"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1806"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1186\/2193-1801-2-526"},{"article-title":"The musdb18 corpus for music separation","year":"2017","author":"rafii","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02154"},{"key":"ref28","first-page":"387","article-title":"Evaluation of algorithms using games: The case of music tagging","author":"law","year":"2009","journal-title":"ISMIR"},{"article-title":"Speechbrain: A general-purpose speech toolkit","year":"2021","author":"ravanelli","key":"ref27"},{"key":"ref29","first-page":"591","article-title":"The million song dataset","author":"bertin-mahieux","year":"2011","journal-title":"ISMIR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2003.10.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414470"},{"article-title":"End-to-end learning for music audio tagging at scale","year":"2017","author":"pons","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414405"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1049\/el:20000192"},{"article-title":"Listen, read, and identify: multi-modal singing language identification of music","year":"2021","author":"choi","key":"ref5"}],"event":{"name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2023,10,22]]},"location":"New Paltz, NY, USA","end":{"date-parts":[[2023,10,25]]}},"container-title":["2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10248019\/10248047\/10248164.pdf?arnumber=10248164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T17:41:07Z","timestamp":1696268467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10248164\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,22]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/waspaa58266.2023.10248164","relation":{},"subject":[],"published":{"date-parts":[[2023,10,22]]}}}