{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T04:01:45Z","timestamp":1748491305531,"version":"3.41.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icasspw65056.2025.11011167","type":"proceedings-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T17:05:14Z","timestamp":1748365514000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Singing Voice Accompaniment Data Augmentation with Generative Models"],"prefix":"10.1109","author":[{"given":"Miguel","family":"Perez","sequence":"first","affiliation":[{"name":"Universitat Pompeu Fabra,Barcelona,Spain"}]},{"given":"Holger","family":"Kirchhoff","sequence":"additional","affiliation":[{"name":"Huawei Munich Research Center,Munich,Germany"}]},{"given":"Peter","family":"Grosche","sequence":"additional","affiliation":[{"name":"Huawei Munich Research Center,Munich,Germany"}]},{"given":"Xavier","family":"Serra","sequence":"additional","affiliation":[{"name":"Universitat Pompeu Fabra,Barcelona,Spain"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Melody extraction from polyphonic signals","volume-title":"Ph.D. dissertation","author":"Salamon","year":"2013"},{"key":"ref2","first-page":"567","article-title":"Evaluation framework for automatic singing transcription","volume-title":"Proceedings of the 15th International Society for Music Information Retrieval Conference, ISMIR 2014, Taipei, Taiwan, October 27-31, 2014","author":"Molina"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746549"},{"article-title":"Simple and controllable music generation","volume-title":"37th Conference on Neural Information Processing Systems","author":"Copet","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096688"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.26"},{"article-title":"Pesto: Pitch estimation with self-supervised transposition-equivariant objective","volume-title":"Proceedings of the 24th International Society for Music Information Retrieval Conference, ISMIR 2023","author":"Riou","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2982285"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"article-title":"Lp-musiccaps: Llm-based pseudo music captioning","volume-title":"Proceedings of the 24th International Society for Music Information Retrieval Conference, ISMIR 2023","author":"Doh","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-2061-6_9"},{"article-title":"Hybrid spectrogram and waveform source separation","volume-title":"Proceedings of the ISMIR 2021 Workshop on Music Source Separation","author":"D\u00e9fossez","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096956"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3224297"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747147"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445858"},{"article-title":"Singsong: Generating musical accompaniments from singing","year":"2023","author":"Donahue","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096239"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02154"},{"key":"ref21","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414601"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3651310"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"}],"event":{"name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2025,4,6]]},"location":"Hyderabad, India","end":{"date-parts":[[2025,4,11]]}},"container-title":["2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11010992\/11010997\/11011167.pdf?arnumber=11011167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T04:53:15Z","timestamp":1748407995000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11011167\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icasspw65056.2025.11011167","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}