{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T18:52:51Z","timestamp":1725735171287},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414203","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"271-275","source":"Crossref","is-referenced-by-count":3,"title":["Singing Language Identification Using a Deep Phonotactic Approach"],"prefix":"10.1109","author":[{"given":"Lenny","family":"Renault","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Vaglio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Romain","family":"Hennequin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-9"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2237151"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947331"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-131"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683470"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1520"},{"key":"ref15","article-title":"Multilingual lyrics-to-audio alignement","author":"vaglio","year":"2020","journal-title":"Proc of the International Conference on Music Information Retrieval (ISMIR)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054278"},{"key":"ref17","first-page":"431","article-title":"DALI: A Large Dataset of Synchronized Audio, Lyrics and notes, Automatically Created using Teacher-student Machine Learning Paradigm","author":"meseguer-brocal","year":"2018","journal-title":"Proc of the International Society for Music Information Retrieval (ISMIR)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268945"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref28","first-page":"857","article-title":"Language recognition via i-vectors and dimensionality reduction","author":"dehak","year":"2011","journal-title":"Proc of the Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"key":"ref4","first-page":"145","article-title":"Nist language recognition evaluation past and future","author":"martin","year":"2014","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref27","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc of Automatic Speech Recognition and Understanding (ASRU 1997)"},{"key":"ref3","first-page":"568","article-title":"Towards Automatic Identification of Singing Language In Popular Music Recordings","author":"tsai","year":"2004","journal-title":"Proc of the International Conference on Music Information Retrieval (ISMIR)"},{"key":"ref6","first-page":"377","article-title":"Language identification in vocal music","author":"schwenninger","year":"2006","journal-title":"Proc of the International Conference on Music Information Retrieval (ISMIR)"},{"article-title":"CTCModel: Connectionist Temporal Classification in Keras","year":"2018","author":"soullard","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2010-546047"},{"key":"ref8","first-page":"140","article-title":"A GMM approach to singing language identification","author":"kruspe","year":"2014","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947660"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101255"},{"key":"ref9","article-title":"Improving singing language identification through I-vector extraction","author":"kruspe","year":"2014","journal-title":"Proc of the International Conference on Digital Audio Effects (DAFx)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.913750"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-16"},{"key":"ref22","article-title":"Gradient flow in recurrent nets: the difficulty of learning long-term dependencies","author":"hochreiter","year":"2001","journal-title":"A Field Guide to Dynamical Recurrent Neural Networks"},{"key":"ref21","first-page":"5991","article-title":"Utterance-level end-to-end language identification using attention-based cnnblstm","author":"cai","year":"2019","journal-title":"Proc IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref24","first-page":"341","article-title":"A closer look on artist filters for musical genre classification","author":"flexer","year":"2007","journal-title":"Proc of the International Conference on Music Information Retrieval (ISMIR)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02154"},{"article-title":"Fasttext.zip: Compressing text classification models","year":"2016","author":"joulin","key":"ref26"},{"article-title":"Phonemizer (version 2.2.1)","year":"2015","author":"bernard","key":"ref25"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414203.pdf?arnumber=9414203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:59Z","timestamp":1652197259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414203","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}