{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:33:49Z","timestamp":1753601629541,"version":"3.37.3"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001352","name":"National University of Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001352","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094717","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Self-Transriber: Few-Shot Lyrics Transcription With Self-Training"],"prefix":"10.1109","author":[{"given":"Xiaoxue","family":"Gao","sequence":"first","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianghu","family":"Yue","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3191845"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref12","first-page":"27 826","article-title":"Unsupervised speech recognition","volume":"34","author":"baevski","year":"2021","journal-title":"Advances in neural information processing sys-terns"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.558"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190742"},{"key":"ref37","article-title":"Attention-based models for speech recognition","volume":"28","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"396","article-title":"Automatic lyrics-to-audio alignment on polyphonic music using singing-adapted acoustic models","author":"gupta","year":"2019","journal-title":"IEEE ICASSP"},{"article-title":"Speechbrain: A general-purpose speech toolkit","year":"2021","author":"ravanelli","key":"ref36"},{"key":"ref31","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00873"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2933146"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548411"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.916370"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2014.00809"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2993893"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref39"},{"key":"ref16","article-title":"Transfer learning of wav2vec 2.0 for automatic lyric transcription","author":"ou","year":"2022","journal-title":"Proc ISMIR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"year":"0","key":"ref19","article-title":"Smule sing! 300x30x2 dataset"},{"article-title":"Digital Archive Mobile Performances (DAMP)","year":"0","author":"smule","key":"ref18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207052"},{"key":"ref23","first-page":"1507","article-title":"Automatic pronunciation evaluation of singing","author":"gupta","year":"2018","journal-title":"InterSpeech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.718"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.426"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2378"},{"key":"ref22","first-page":"600","article-title":"Semi-supervised lyrics and solo-singing alignment","author":"gupta","year":"2018","journal-title":"ISMIR"},{"key":"ref21","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1280"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414641"},{"key":"ref8","first-page":"281","article-title":"Modeling of phoneme durations for alignment between polyphonic audio and lyrics","author":"dzhambazov","year":"2015","journal-title":"Sound and Music Computing Conference"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2010-546047"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747684"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-36"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023056"},{"key":"ref6","article-title":"Music-robust automatic lyrics transcription of polyphonic music","author":"gao","year":"2022","journal-title":"Proc SMC"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SpeD.2013.6682644"},{"key":"ref40","article-title":"Mstre-net: Multistreaming acoustic modeling for automatic lyrics transcription","author":"demirel","year":"2021","journal-title":"Proc ISMIR"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094717.pdf?arnumber=10094717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:56:54Z","timestamp":1699901814000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094717","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}