{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:56:04Z","timestamp":1776887764275,"version":"3.51.2"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10445858","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"341-345","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing Note-Level Singing Transcription Model with Unlabeled and Weakly Labeled Data"],"prefix":"10.1109","author":[{"given":"Yao","family":"Qiu","sequence":"first","affiliation":[{"name":"Tencent WeChatAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent WeChatAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Shan","sequence":"additional","affiliation":[{"name":"Tencent WeChatAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tencent WeChatAI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"737","article-title":"Singing voice melody transcription using deep neural networks","volume-title":"ISMIR","author":"Rigaud"},{"key":"ref2","first-page":"36","article-title":"An audio front end for query-by-humming systems","volume-title":"Proceedings of International Symposium on Music Information Retrieval","author":"Haus"},{"key":"ref3","author":"Mauch","year":"2015","journal-title":"Computer-aided melody note transcription using the tony software: Accuracy and efficiency"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3224297"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414601"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952166"},{"key":"ref9","first-page":"900","article-title":"Hierarchical classification networks for singing voice segmentation and transcription","volume-title":"Proceedings of the 20th International Society for Music Information Retrieval Conference (ISMIR 2019)","author":"Fu"},{"key":"ref10","author":"Molina","year":"2014","journal-title":"Evaluation framework for automatic singing transcription"},{"key":"ref11","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414996"},{"key":"ref13","first-page":"12449","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":"ref14","first-page":"3","article-title":"Constant-q transform toolbox for music processing","volume-title":"7th sound and music computing conference, Barcelona, Spain","author":"Sch\u00f6rkhuber"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03391"},{"key":"ref16","author":"Ravanelli","year":"2021","journal-title":"Speech-Brain: A general-purpose speech toolkit"},{"key":"ref17","first-page":"6914","article-title":"M4singer: A multi-style, multi-singer and musical score provided mandarin singing corpus","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref20","article-title":"Pop909: A pop-song dataset for music arrangement generation","author":"Wang","year":"2020"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10445858.pdf?arnumber=10445858","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:57:12Z","timestamp":1722574632000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445858\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445858","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}