{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:37:43Z","timestamp":1763192263421,"version":"3.45.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11231014","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Class-Token Transformer for Multitask Self-supervised Music Information Retrieval"],"prefix":"10.1109","author":[{"given":"Yuexuan","family":"Kong","sequence":"first","affiliation":[{"name":"Deezer Research,Paris,France"}]},{"given":"Vincent","family":"Lostanlen","sequence":"additional","affiliation":[{"name":"Nantes Université,Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France,F-44000"}]},{"given":"Romain","family":"Hennequin","sequence":"additional","affiliation":[{"name":"Deezer Research,Paris,France"}]},{"given":"Mathieu","family":"Lagrange","sequence":"additional","affiliation":[{"name":"Nantes Université,Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France,F-44000"}]},{"given":"Gabriel","family":"Meseguer-Brocal","sequence":"additional","affiliation":[{"name":"Deezer Research,Paris,France"}]}],"member":"263","reference":[{"article-title":"A cookbook of self-supervised learning","year":"2023","author":"Balestriero","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447473"},{"article-title":"Contrastive learning of musical representations","volume-title":"Proc. International Society for Music Information Retrieval (ISMIR) Conference","author":"Spijkervet","key":"ref3"},{"article-title":"Supervised and unsupervised learning of audio representations for music understanding","volume-title":"Proc. International Society for Music Information Retrieval Conference (ISMIR)","author":"McCallum","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890270"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859799"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11674-2_5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3297963"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2982285"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.251"},{"article-title":"Equivariant self-supervision for musical tempo estimation","volume-title":"Proc. International Society for Music Information Retrieval Conference (ISMIR)","author":"Quinton","key":"ref11"},{"article-title":"Mert: Acoustic music understanding model with large-scale self-supervised training","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Li","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448314"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2011.603834"},{"article-title":"Transfer learning in MIR: Sharing learned latent representations for music audio classification and similarity","volume-title":"Proc. International Society for Music Information Retrieval Conference (ISMIR)","author":"Hamel","key":"ref15"},{"article-title":"Cross task study on MIREX recent results: An index for evolution measurement and some stagnation hypotheses","volume-title":"Proc. International Society for Music Information Retrieval Conference (ISMIR)","author":"Scholz","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683426"},{"article-title":"Multitask learning based deep learning model for music artist and language recognition","volume-title":"Proc. Workshop on Speech and Music Processing (SMP)","author":"Singh","key":"ref18"},{"key":"ref19","first-page":"125","article-title":"HEAR: Holistic evaluation of audio representations","volume-title":"Proceeedings of the Neural Information Processing Systems Conference (NeurIPS), Competitions and Demonstrations Track","author":"Turian"},{"article-title":"Emergent musical properties of a transformer under contrastive self-supervised learning","volume-title":"International Society for Music Information Retrieval Conference (ISMIR 2025)","author":"Kong","key":"ref20"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Dosovitskiy","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"article-title":"STONE: Self-supervised tonality estimator","volume-title":"Proc. International Society for Music Information Retrieval Conference (ISMIR)","author":"Kong","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890222"},{"article-title":"Deep salience representations for f 0 estimation in polyphonic music","volume-title":"Proc. 18th International Society for Music Information Retrieval Conference (ISMIR)","author":"Bittner","key":"ref25"},{"article-title":"Vision transformers need registers","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Darcet","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3404422"},{"key":"ref28","first-page":"213","article-title":"Evaluation of algorithms using games: The case of music tagging","volume-title":"Proc. International Society for Music Information Retrieval Conference (ISMIR)","author":"Law"},{"article-title":"Sample-level deep convolutional neural networks for music auto-tagging using raw waveforms","volume-title":"Proc. International Conference on Sound and Music Computing (SMC)","author":"Lee","key":"ref29"},{"article-title":"Orchideasol: A dataset of extended instrumental techniques for computer-aided orchestration","volume-title":"Proc. International Computer Music Conference (ICMC)","author":"Cella","key":"ref30"},{"article-title":"Fmak: A dataset of key and mode annotations for the free music archive \u2014 extended abstract","volume-title":"Proc. 24th International Society for Music Information Retrieval (ISMIR) Late-Breaking\/Demo Papers","author":"Wong","key":"ref31"},{"article-title":"Fma: A dataset for music analysis","volume-title":"Proc. International Society for Music Information Retrieval Conference (ISMIR)","author":"Defferrard","key":"ref32"},{"article-title":"Two datasets for tempo estimation and key detection in electronic dance music annotated from user corrections","volume-title":"Proc. International Society for Music Information Retrieval Conference (ISMIR)","author":"Knees","key":"ref33"},{"key":"ref34","first-page":"2014","article-title":"mir eval: A transparent implementation of common mir metrics","volume-title":"Proc. International Society for Music Information Retrieval Conference (ISMIR)","volume":"10","author":"Raffel"},{"article-title":"A review of rhythm description systems","volume-title":"Proc. International Society for Music Information Retrieval Conference (ISMIR)","author":"Gouyon","key":"ref35"},{"article-title":"Gtzan-rhythm: Extending the gtzan test-set with beat, downbeat and swing annotations","volume-title":"Proc. International Society for Music Information Retrieval Late-breaking\/Demo (ISMIR-LBD)","author":"Marchand","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3429743"},{"article-title":"RWC music database: Popular, classical, and jazz music databases","volume-title":"Proc. International Society for Music Information Retrieval Conference (ISMIR)","author":"Goto","key":"ref38"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2025,10,12]]},"location":"Tahoe City, CA, USA","end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11231014.pdf?arnumber=11231014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:32:57Z","timestamp":1763191977000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11231014\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11231014","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}