{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:06:49Z","timestamp":1776881209332,"version":"3.51.2"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11230979","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models"],"prefix":"10.1109","author":[{"given":"Riccardo","family":"Passoni","sequence":"first","affiliation":[{"name":"Informazione e Bioingegneria - Politecnico di Milano,Dipartimento di Elettronica,Milan,Italy"}]},{"given":"Francesca","family":"Ronchini","sequence":"additional","affiliation":[{"name":"Informazione e Bioingegneria - Politecnico di Milano,Dipartimento di Elettronica,Milan,Italy"}]},{"given":"Luca","family":"Comanducci","sequence":"additional","affiliation":[{"name":"Informazione e Bioingegneria - Politecnico di Milano,Dipartimento di Elettronica,Milan,Italy"}]},{"given":"Romain","family":"Serizel","sequence":"additional","affiliation":[{"name":"Université de Lorraine,CNRS, Inria, Loria,Nancy,France"}]},{"given":"Fabio","family":"Antonacci","sequence":"additional","affiliation":[{"name":"Informazione e Bioingegneria - Politecnico di Milano,Dipartimento di Elettronica,Milan,Italy"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2908700"},{"key":"ref2","volume-title":"Generative AI for Music and Audio","author":"Dong","year":"2024"},{"key":"ref3","article-title":"Foundation models for music: A survey","author":"Ma","year":"2024"},{"key":"ref4","article-title":"Energy consumption of deep generative audio models","author":"Douwes","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889562"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21428\/bf6fb269.1f033948"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3381831"},{"key":"ref8","article-title":"Green mir?: Investigating computational cost of recent music-ai research in ismir","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Holzapfel"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096975"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095938"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-456"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TTS.2024.3513777"},{"key":"ref13","article-title":"Monitoring environmental impact of dcase systems: Why and how?","volume-title":"Detection and Classification of Acoustic Scene and Events (DCASE) Workshop","author":"Douwes"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445834"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658542"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref17","article-title":"The environmental impact of deep learning for audio","author":"Douwes","year":"2023"},{"key":"ref18","first-page":"21 450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proceedings of the 40th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"202","author":"Liu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3399607"},{"key":"ref21","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, ser. ICML\u201923","author":"Huang"},{"key":"ref22","article-title":"Make-an-audio 2: Temporal-enhanced text-to-audio generation","volume-title":"CoRR","author":"Huang","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref24","article-title":"The flan collection: Designing data and methods for effective instruction tuning","volume-title":"International Conference on Machine Learning","author":"Longpre"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888461"},{"key":"ref26","article-title":"Carbontracker: Tracking and predicting the carbon footprint of training deep learning models","author":"Anthony","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref28","article-title":"Codecarbon: estimate and track carbon emissions from machine learning computing","volume":"20","author":"Schmidt","year":"2021","journal-title":"Cited on"},{"key":"ref29","article-title":"Thop: Pytorch-opcounter","author":"Zhu","year":"2019"},{"key":"ref30","article-title":"mlco2\/codecarbon: v2.4.1","author":"Courty","year":"2024"},{"key":"ref31","article-title":"From computation to consumption: Exploring the compute-energy link for training and testing neural networks for sed systems","author":"Douwes","year":"2024"},{"key":"ref32","article-title":"Fr\\ \u2019echet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref36","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Fr\\ \u2019echet audio distance: A reference-free metric for evaluating music enhancement algorithms","volume-title":"Proc. Interspeech","author":"Roblek"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP48485.2024.10446663","article-title":"Adapting frechet audio distance for generative music evaluation","volume-title":"Proc. IEEE ICASSP 2024","author":"Gui"},{"key":"ref39","article-title":"Stable audio metrics toolkit","author":"AI","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14173379"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642040"},{"key":"ref42","article-title":"Freesound datasets: A platform for the creation of open audio datasets","volume-title":"ISMIR","author":"Fonseca"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"Tahoe City, CA, USA","start":{"date-parts":[[2025,10,12]]},"end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11230979.pdf?arnumber=11230979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:17:59Z","timestamp":1763191079000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230979\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11230979","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}