{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:40:32Z","timestamp":1779385232664,"version":"3.53.1"},"reference-count":50,"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\/icassp49660.2025.10888146","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations"],"prefix":"10.1109","author":[{"given":"Ruben","family":"Ciranni","sequence":"first","affiliation":[{"name":"Sapienza University of Rome,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giorgio","family":"Mariani","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michele","family":"Mancusi","sequence":"additional","affiliation":[{"name":"Sony Europe B.V.,Stuttgart,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emilian","family":"Postolache","sequence":"additional","affiliation":[{"name":"Ca’ Foscari University of Venice,DAIS,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giorgio","family":"Fabbro","sequence":"additional","affiliation":[{"name":"Sony Europe B.V.,Stuttgart,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emanuele","family":"Rodol\u00e0","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Cosmo","sequence":"additional","affiliation":[{"name":"Ca’ Foscari University of Venice,DAIS,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Mo\u00fbsai: Text-to-music generation with long-context latent diffusion","author":"Schneider","year":"2023"},{"key":"ref2","article-title":"Vampnet: Music generation via masked acoustic token modeling","author":"Garcia","year":"2023"},{"key":"ref3","article-title":"Fast timing-conditioned latent audio diffusion","author":"Evans","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888461"},{"key":"ref5","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref6","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Ho"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"issue":"140","key":"ref8","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref9","article-title":"Multi-source diffusion models for simultaneous music generation and separation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Mariani"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/645"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446088"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/app10186627"},{"key":"ref13","article-title":"Singsong: Generating musical accompaniments from singing","author":"Donahue","year":"2023"},{"key":"ref14","first-page":"2350","article-title":"Fr\u00e9chet audio distance: A reference-free metric for evaluating music enhancement algorithms","volume-title":"Proc. Interspeech","author":"Roblek"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref16","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref17","article-title":"COALA: Co-aligned autoencoders for learning semantically enriched audio representations","volume-title":"ICML 2020 Workshop on Self-supervision in Audio and Speech","author":"Favory"},{"key":"ref18","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746996"},{"key":"ref20","article-title":"Contrastive audio-language learning for music","volume-title":"Ismir 2022 Hybrid Conference","author":"Manco"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref23","first-page":"28 708","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref25","article-title":"Contrastive learning of musical representations","volume-title":"Ismir 2021","author":"Spijkervet"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref27","article-title":"Multi-source contrastive learning from musical audio","author":"Garoufis","year":"2023"},{"key":"ref28","article-title":"Neural loop combiner: Neural network models for assessing the compatibility of loops","author":"Chen","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16092"},{"key":"ref30","article-title":"Samplematch: Drum sample retrieval by musical context","volume-title":"Ismir 2022 Hybrid Conference","author":"Lattner"},{"key":"ref31","article-title":"Stem-jepa: A joint-embedding predictive architecture for musical stem compatibility estimation","author":"Riou","year":"2024"},{"key":"ref32","article-title":"Diff-a-riff: Musical accompaniment co-creation via latent diffusion models","author":"Nistal","year":"2024"},{"key":"ref33","first-page":"4724","article-title":"Source separation with deep generative priors","volume-title":"International Conference on Machine Learning","author":"Jayaram"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3219355"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26131"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447122"},{"key":"ref37","article-title":"Instruct-musicgen: Unlocking text-to-music editing for music language models via instruction tuning","author":"Zhang","year":"2024"},{"key":"ref38","article-title":"Audit: Audio editing by following instructions with latent diffusion models","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","article-title":"Moisesdb: A dataset for source separation beyond 4 stems","volume-title":"Ismir 2023 Hybrid Conference","author":"Pereira"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937170"},{"key":"ref41","article-title":"The chamber ensemble generator: Limitless high-quality mir data via generative modeling","author":"Wu","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref43","first-page":"246","article-title":"Harmonic\/percussive separation using median filtering","volume-title":"Proceedings of the International Conference on Digital Audio Effects (DAFx)","author":"FitzGerald"},{"key":"ref44","article-title":"Musdb18-hq - an uncompressed version of musdb18","author":"Rafii","year":"2019"},{"key":"ref45","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref47","article-title":"The mtg-jamendo dataset for automatic music tagging","volume-title":"Machine Learning for Music Discovery Workshop, International Conference on Machine Learning (ICML 2019)","author":"Bogdanov"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446663"},{"key":"ref49","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref50","article-title":"Ensembleset: a new high quality synthesised dataset for chamber ensemble separation","volume-title":"Ismir 2022 Hybrid Conference","author":"Sarkar"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888146.pdf?arnumber=10888146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:43Z","timestamp":1774416343000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888146","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}