{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:26:43Z","timestamp":1774420003473,"version":"3.50.1"},"reference-count":36,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887744","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":0,"title":["Subtractive Training for Music Stem Insertion Using Latent Diffusion Models"],"prefix":"10.1109","author":[{"given":"Ivan","family":"Villa-Renteria","sequence":"first","affiliation":[{"name":"Stanford University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mason Long","family":"Wang","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zachary","family":"Shah","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Li","sequence":"additional","affiliation":[{"name":"Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soohyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neelesh","family":"Ramachandran","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mert","family":"Pilanci","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020"},{"key":"ref2","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref3","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"Noise2music: Text-conditioned music generation with diffusion models","author":"Huang","year":"2023"},{"key":"ref5","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref7","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344972"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-019-10163-0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109046"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref15","article-title":"Wavenet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref16","article-title":"Riffusion - Stable diffusion for real-time music generation","author":"Forsgren","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"ref18","article-title":"Vampnet: Music generation via masked acoustic token modeling","author":"Garcia","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/851"},{"key":"ref20","article-title":"Instruct-musicgen: Unlocking text-to-music editing for music language models via instruction tuning","author":"Zhang","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/645"},{"key":"ref22","article-title":"Joint audio and symbolic conditioning for temporally controlled text-to-music generation","author":"Tal","year":"2024"},{"key":"ref23","article-title":"Content-based controls for music large language modeling","author":"Lin","year":"2023"},{"key":"ref24","article-title":"Diffa-riff: Musical accompaniment co-creation via latent diffusion models","author":"Nistal","year":"2024"},{"key":"ref25","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref26","article-title":"Lp-musiccaps: Llm-based pseudo music captioning","author":"Doh","year":"2023"},{"key":"ref27","article-title":"The musdb18 corpus for music separation","author":"Rafii","year":"2017"},{"key":"ref28","first-page":"387","article-title":"Evaluation of algorithms using games: The case of music tagging","volume-title":"ISMIR","author":"Law"},{"key":"ref29","article-title":"Demucs: Deep extractor for music sources with extra unlabeled data remixed","author":"D\u00e9fossez","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref31","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref34","article-title":"Evaluating generative audio systems and their metrics","author":"Vinay","year":"2022"},{"key":"ref35","article-title":"Generating symbolic music using diffusion models","author":"Atassi","year":"2023"},{"key":"ref36","article-title":"Dadagp: a dataset of tokenized guitarpro songs for sequence models","author":"Sarmento","year":"2021"}],"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\/10887744.pdf?arnumber=10887744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:53Z","timestamp":1774416353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887744","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}