{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:25:16Z","timestamp":1774419916071,"version":"3.50.1"},"reference-count":47,"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\/icassp49660.2025.10887735","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Naturalistic Music Decoding from EEG Data via Latent Diffusion Models"],"prefix":"10.1109","author":[{"given":"Emilian","family":"Postolache","sequence":"first","affiliation":[{"name":"DAIS Ca' Foscari University of Venice Venice,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Natalia","family":"Polouliakh","sequence":"additional","affiliation":[{"name":"Sony CSL,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroaki","family":"Kitano","sequence":"additional","affiliation":[{"name":"Sony CSL,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akima","family":"Connelly","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology,Dept. of TSE,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuele","family":"Rodol\u00e0","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome,Dept. of Computer Science,Rome,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Cosmo","sequence":"additional","affiliation":[{"name":"DAIS Ca' Foscari University of Venice Venice,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taketo","family":"Akama","sequence":"additional","affiliation":[{"name":"Sony CSL,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Brain2music: Reconstructing music from human brain activity","author":"Denk","year":"2023"},{"key":"ref2","article-title":"Mulan: A joint embedding of music audio and natural language","volume-title":"Ismir 2022 Hybrid Conference","author":"Huang"},{"key":"ref3","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.3002176"},{"key":"ref5","article-title":"Biosignal sensing device using dynamic selection of electrodes","volume-title":"Patent","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-27361-x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00714-5"},{"key":"ref9","article-title":"Generative modeling by estimating gradients of the data distribution","volume":"32","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref13","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"International Conference on Learning Representations","author":"Kong"},{"key":"ref14","article-title":"Wavegrad: Estimating gradients for waveform generation","volume-title":"International Conference on Learning Representations","author":"Chen"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096760"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3399607"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447063"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447380"},{"key":"ref19","article-title":"Video-foley: Two-stage video-to- sound generation via temporal event condition for foley sound","author":"Lee","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095310"},{"key":"ref21","article-title":"Separate and diffuse: Using a pretrained diffusion model for better source separation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lutati"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095103"},{"key":"ref23","article-title":"Mo\u00fcsai: Text-to-music generation with long-context latent diffusion","author":"Schneider","year":"2023"},{"key":"ref24","article-title":"Fast timing- conditioned latent audio diffusion","author":"Evans","year":"2024"},{"key":"ref25","article-title":"Multi-source diffusion models for simultaneous music generation and separation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Mariani"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/645"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447122"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446088"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888146"},{"key":"ref30","article-title":"Dreamdiffusion: Generating high-quality images from brain eeg signals","author":"Bai","year":"2023"},{"key":"ref31","article-title":"Seeing through the brain: Image reconstruction of visual perception from human brain signals","author":"Lan","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2024.3516698"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28519"},{"key":"ref35","article-title":"Nmed-t: A tempo-focused dataset of cortical and behavioral responses to naturalistic music","volume-title":"International Society for Music Information Retrieval Conference","author":"Losorelli"},{"key":"ref36","first-page":"11 287","article-title":"Score-based generative modeling in latent space","volume":"34","author":"Vahdat","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Auto-encoding variational bayes","volume-title":"2nd International Conference on Learning Representations, ICLR 2014","author":"Kingma"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref39","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref42","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref43","first-page":"2350","article-title":"Fr\\\u2019echet audio distance: A reference-free metric for evaluating music enhancement algorithms","volume-title":"Proc. Interspeech","author":"Roblek"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446663"},{"issue":"3","key":"ref46","first-page":"154","article-title":"Spatial sampling of head electrical fields: the geodesic sensor net","volume-title":"Electroencephalography and Clinical Neurophysiology","volume":"87","author":"Tucker","year":"1993"},{"key":"ref47","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"}],"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\/10887735.pdf?arnumber=10887735","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:24Z","timestamp":1774416324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887735\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887735","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}