{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:34:16Z","timestamp":1783737256661,"version":"3.55.0"},"reference-count":40,"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\/icassp48485.2024.10448314","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1226-1230","source":"Crossref","is-referenced-by-count":25,"title":["A Foundation Model for Music Informatics"],"prefix":"10.1109","author":[{"given":"Minz","family":"Won","sequence":"first","affiliation":[{"name":"ByteDance,SAMI,San Jose,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun-Ning","family":"Hung","sequence":"additional","affiliation":[{"name":"ByteDance,SAMI,San Jose,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duc","family":"Le","sequence":"additional","affiliation":[{"name":"ByteDance,SAMI,San Jose,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Bommasani","year":"2021","journal-title":"On the opportunities and risks of foundation models"},{"key":"ref2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref3","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"Proc. ICML","author":"Chiu"},{"key":"ref8","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref9","article-title":"Semi-supervised music tagging transformer","volume-title":"Proc. ISMIR","author":"Won"},{"key":"ref10","article-title":"Semi-supervised learning using teacher-student models for vocal melody extraction","volume-title":"Proc. ISMIR","author":"Kum"},{"key":"ref11","article-title":"Transfer learning by supervised pre-training for audio-based music classification","volume-title":"Proc. ISMIR","author":"Van Den Oord"},{"key":"ref12","article-title":"Transfer learning for music classification and regression tasks","volume-title":"Proc. ISMIR","author":"Choi"},{"key":"ref13","article-title":"Supervised and unsupervised learning of audio representations for music understanding","volume-title":"Proc. ISMIR","author":"McCallum"},{"key":"ref14","article-title":"Contrastive learning of musical representations","volume-title":"Proc. ISMIR","author":"Spijkervet"},{"key":"ref15","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref16","article-title":"Codified audio language modeling learns useful representations for music information retrieval","volume-title":"Proc. ISMIR","author":"Castellon"},{"key":"ref17","author":"Dhariwal","year":"2020","journal-title":"Jukebox: A generative model for music"},{"key":"ref18","author":"Li","year":"2023","journal-title":"Mert: Acoustic music understanding model with large-scale self-supervised training"},{"key":"ref19","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"},{"key":"ref20","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","volume-title":"NeurIPS SAS Workshop","author":"Zhang"},{"key":"ref21","author":"D\u00e9fossez","year":"2022","journal-title":"High fidelity neural audio compression"},{"key":"ref22","article-title":"FMA: A dataset for music analysis","volume-title":"Proc. ISMIR","author":"Defferrard"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747048"},{"key":"ref24","article-title":"Joint beat and downbeat tracking with recurrent neural networks","volume-title":"Proc. ISMIR","author":"B\u00f6ck"},{"key":"ref25","article-title":"The Harmonix Set: Beats, downbeats, and functional segment annotations of western popular music","volume-title":"Proc. ISMIR","author":"Nieto"},{"key":"ref26","article-title":"Gtzan-rhythm: Extending the gtzan test-set with beat, downbeat and swing annotations","author":"Marchand","year":"2015","journal-title":"ISMIR Late Breaking and Demo"},{"key":"ref27","article-title":"Mir_eval: A transparent implementation of common mir metrics","volume-title":"Proc. ISMIR","author":"Raffel"},{"key":"ref28","first-page":"485","article-title":"Melody transcription via generative pre-training","volume-title":"Proc. ISMIR","author":"Donahue"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747252"},{"key":"ref30","article-title":"Two data sets for tempo estimation and key detection in electronic dance music annotated from user corrections","volume-title":"Proc. ISMIR","author":"Knees"},{"key":"ref31","author":"Won","year":"2021","journal-title":"Music classification: beyond supervised learning, towards real-world applications"},{"key":"ref32","article-title":"Evaluation of algorithms using games: The case of music tagging","volume-title":"Proc. ISMIR","author":"Law"},{"key":"ref33","article-title":"Evaluation of cnn-based automatic music tagging models","volume-title":"Proc. SMC","author":"Won"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref36","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","first-page":"620","article-title":"A bi-directional transformer for musical chord recognition","volume-title":"Proc. ISMIR","author":"Park"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248148"},{"key":"ref39","article-title":"Genre-agnostic key classification with convolutional neural networks","volume-title":"Proc. ISMIR","author":"Korzeniowski"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095058"}],"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\/10448314.pdf?arnumber=10448314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:43:04Z","timestamp":1722660184000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448314\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448314","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}