{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:14:32Z","timestamp":1776885272399,"version":"3.51.2"},"reference-count":45,"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\/icassp49660.2025.10888864","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":4,"title":["MambaFoley: Foley Sound Generation using Selective State-Space Models"],"prefix":"10.1109","author":[{"given":"Marco Furio","family":"Colombo","sequence":"first","affiliation":[{"name":"Politecnico di Milano,Informazione e Bioingegneria (DEIB),Dipartimento di Elettronica,Milan,Italy,20133"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesca","family":"Ronchini","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Informazione e Bioingegneria (DEIB),Dipartimento di Elettronica,Milan,Italy,20133"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Comanducci","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Informazione e Bioingegneria (DEIB),Dipartimento di Elettronica,Milan,Italy,20133"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Antonacci","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Informazione e Bioingegneria (DEIB),Dipartimento di Elettronica,Milan,Italy,20133"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"NIPS","author":"Ho"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3399607"},{"key":"ref4","article-title":"Make-an-audio: text-to-audio generation with prompt-enhanced diffusion models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Huang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446761"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1350"},{"key":"ref7","article-title":"Synthetic training set generation using text-to-audio models for environmental sound classification","author":"Ronchini","year":"2024"},{"key":"ref8","article-title":"Foley sound synthesis at the dcase 2023 challenge","volume-title":"DCASE - Workshop on Detection and Classification of Acoustic Scenes and Events","author":"Choi"},{"key":"ref9","article-title":"Fall-e: A foley sound synthesis model and strategies","volume-title":"DCASE - Workshop on Detection and Classification of Acoustic Scenes and Events)","author":"Kang"},{"key":"ref10","article-title":"Foley sound synthesis with a class-conditioned latent diffusion model","volume-title":"DCASE - Workshop on Detection and Classification of Acoustic Scenes and Events","author":"Scheibler"},{"key":"ref11","article-title":"Text-driven foley sound generation with latent diffusion model","volume-title":"DCASE - Workshop on Detection and Classification of Acoustic Scenes and Events","author":"Yuan"},{"key":"ref12","article-title":"Foley sound synthesis based on generative adversarial networks using oneself-conditioned contrastive learning","volume-title":"DCASE - Workshop on Detection and Classification of Acoustic Scenes and Events","author":"Chung"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447063"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447380"},{"key":"ref15","article-title":"Picoaudio: Enabling precise timestamp and frequency controllability of audio events in text-to-audio generation","author":"Xie","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889879"},{"key":"ref17","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","volume-title":"ICLR","author":"Mehri"},{"key":"ref18","article-title":"Wavenet: A generative model for raw audio","author":"Van Den Oord","year":"2016"},{"key":"ref19","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019"},{"key":"ref20","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","author":"Gu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"ICLR","author":"Gu"},{"key":"ref23","first-page":"7616","article-title":"It\u2019s raw! audio generation with state-space models","volume-title":"International Conference on Machine Learning","author":"Goel"},{"key":"ref24","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref25","article-title":"Transformers are ssms: generalized models and efficient algorithms through structured state space duality","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Dao"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1274"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-698"},{"key":"ref28","article-title":"Spmamba: State-space model is all you need in speech separation","author":"Li","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096760"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref31","article-title":"Hydra: Bidirectional state space models through generalized matrix mixers","author":"Hwang","year":"2024","journal-title":"NIPS. Neural Information Processing Systems"},{"key":"ref32","article-title":"Root mean square layer normalization","volume":"32","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref35","article-title":"Bbc sound effects dataset"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Diederik"},{"key":"ref37","first-page":"579","article-title":"Crash: Raw audio score-based generative modeling for controllable high-resolution drum sound synthesis","volume-title":"ISMIR","author":"Rouard","year":"2021"},{"key":"ref38","article-title":"Variational diffusion models","volume-title":"CoRR","author":"Kingma","year":"2021"},{"key":"ref39","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref40","article-title":"Fr\u00e9chet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2019"},{"key":"ref41","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Heusel","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/eusipco63174.2024.10714935"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446663"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"}],"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\/10888864.pdf?arnumber=10888864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:41Z","timestamp":1774416281000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888864","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}