{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T14:56:12Z","timestamp":1777733772667,"version":"3.51.4"},"reference-count":33,"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\/icassp49660.2025.10888461","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":67,"title":["Stable Audio Open"],"prefix":"10.1109","author":[{"given":"Zach","family":"Evans","sequence":"first","affiliation":[{"name":"Stability AI"}]},{"given":"Julian D.","family":"Parker","sequence":"additional","affiliation":[{"name":"Stability AI"}]},{"given":"CJ","family":"Carr","sequence":"additional","affiliation":[{"name":"Stability AI"}]},{"given":"Zack","family":"Zukowski","sequence":"additional","affiliation":[{"name":"Stability AI"}]},{"given":"Josiah","family":"Taylor","sequence":"additional","affiliation":[{"name":"Stability AI"}]},{"given":"Jordi","family":"Pons","sequence":"additional","affiliation":[{"name":"Stability AI"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Audiogen: Textually guided audio generation","author":"Kreuk","year":"2022"},{"key":"ref2","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3399607"},{"key":"ref4","article-title":"Fast timing-conditioned latent audio diffusion","volume-title":"ICML","author":"Evans"},{"key":"ref5","article-title":"Long-form music generation with latent diffusion","author":"Evans","year":"2024"},{"key":"ref6","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref7","article-title":"Controllable music production with diffusion models and guidance gradients","author":"Levy","year":"2023"},{"key":"ref8","article-title":"AudioSet: An ontology and humanlabeled dataset for audio events","volume-title":"ICASSP","author":"Gemmeke"},{"key":"ref9","article-title":"Simple and controllable music generation","author":"Copet","year":"2023"},{"key":"ref10","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref12","article-title":"Neural networks fail to learn periodic functions and how to fix it","author":"Ziyin","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref15","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","author":"Dao","year":"2022"},{"key":"ref16","article-title":"Training deep nets with sublinear memory cost","author":"Chen","year":"2016"},{"key":"ref17","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref20","article-title":"Audiogenai\/agc: Audiogen codec"},{"key":"ref21","article-title":"Highfidelity audio compression with improved rvqgan","author":"Kumar","year":"2024","journal-title":"NeurIPS"},{"key":"ref22","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref23","article-title":"auraloss: Audio focused loss functions in PyTorch","author":"Steinmetz","year":"2020","journal-title":"DMRN+15"},{"key":"ref24","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-227"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2219"},{"key":"ref29","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","author":"Huang","year":"2023"},{"key":"ref30","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Conf. of the North American Chapter of the Association for Computational Linguistics","author":"Kim"},{"key":"ref31","article-title":"The Song Describer Dataset: a corpus of audio captions for music-andlanguage evaluation","author":"Manco","year":"2023"},{"key":"ref32","article-title":"Extracting training data from diffusion models","volume-title":"USENIX Security Symposium","author":"Carlini"},{"key":"ref33","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"}],"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\/10888461.pdf?arnumber=10888461","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:59Z","timestamp":1774416359000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888461\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888461","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}