{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T23:10:29Z","timestamp":1765667429236,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096975","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["Is Quality Enough\u0192 Integrating Energy Consumption in a Large-Scale Evaluation of Neural Audio Synthesis Models"],"prefix":"10.1109","author":[{"given":"Constance","family":"Douwes","sequence":"first","affiliation":[{"name":"Sorbonne Universit&#x00E9;, CNRS,IRCAM,Paris,France,F-75004"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni","family":"Bindi","sequence":"additional","affiliation":[{"name":"Sorbonne Universit&#x00E9;, CNRS,IRCAM,Paris,France,F-75004"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antoine","family":"Caillon","sequence":"additional","affiliation":[{"name":"Sorbonne Universit&#x00E9;, CNRS,IRCAM,Paris,France,F-75004"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philippe","family":"Esling","sequence":"additional","affiliation":[{"name":"Sorbonne Universit&#x00E9;, CNRS,IRCAM,Paris,France,F-75004"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Pierre","family":"Briot","sequence":"additional","affiliation":[{"name":"Sorbonne Universit&#x00E9;,CNRS,Paris,France,F-75005"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Green AI","author":"schwartz","year":"2019"},{"key":"ref12","article-title":"Carbontracker: Tracking and predicting the carbon footprint of training deep learning models","author":"wolff anthony","year":"2020","journal-title":"ICML Workshop on Challenges in Deploying and monitoring Machine Learning Systems"},{"key":"ref15","article-title":"Generative adversarial nets","volume":"3","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"1","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"2nd International Conference on Learning Representations ICLR 2014 - Conference Track Proceedings"},{"key":"ref31","first-page":"9041","article-title":"Sing: Symbol-to-instrument neural generator","volume":"2018 decem","author":"d\u00e9fossez","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015 San Diego CA USA May 7-9 2015 Conference Track Proceedings"},{"article-title":"Quantifying the Carbon Emissions of Machine Learning","year":"2019","author":"lacoste","key":"ref11"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/5284645"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9891914"},{"article-title":"Ai and compute","year":"2018","author":"dario","key":"ref1"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"1530","article-title":"Variational inference with normalizing flows","volume":"2","author":"rezende","year":"2015","journal-title":"32nd International Conference on Machine Learning ICML 2015"},{"key":"ref19","first-page":"1","article-title":"Samplernn: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2016","journal-title":"5th International Conference on Learning Representations ICLR 2017 - Conference Track Proceedings"},{"key":"ref18","first-page":"1","article-title":"WaveNet: A Generative Model for Raw Audio","author":"den oord","year":"2016"},{"key":"ref24","first-page":"5852","article-title":"FloWaveNet: A generative flow for raw audio","volume":"2019 june","author":"kim","year":"2019","journal-title":"36th International Conference on Machine Learning ICML 2019"},{"key":"ref23","first-page":"7706","article-title":"Wave-Flow: A compact flow-based model for raw audio","author":"ping","year":"0","journal-title":"Proceedings of the 37th International Conference on Machine Learning 2020 vol 119 of Proceedings of Machine Learning Research"},{"key":"ref26","article-title":"Wavegrad: Estimating gradients for waveform generation","author":"chen","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref25","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"kong","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref20","first-page":"1771","article-title":"Neural audio synthesis of musical notes with WaveNet au-toencoders","volume":"3","author":"engel","year":"2017","journal-title":"International Conference on Machine Learning ICML 2017"},{"key":"ref22","first-page":"1","article-title":"GANSynth: Adversarial neural audio synthesis","author":"engel","year":"2019","journal-title":"7th International Conference on Learning Representations ICLR 2019"},{"key":"ref21","first-page":"1","article-title":"Adversarial audio synthesis","author":"donahue","year":"2019","journal-title":"7th International Conference on Learning Representations ICLR 2019"},{"key":"ref28","first-page":"3617","article-title":"Waveg-low: A Flow-based Generative Network for Speech Synthesis","volume":"2019 may","author":"prenger","year":"2019","journal-title":"ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings"},{"key":"ref27","first-page":"14881","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"NeurIPS"},{"article-title":"The LJ speech dataset","year":"2017","author":"ito","key":"ref29"},{"key":"ref8","first-page":"7616","article-title":"It&#x2019;s raw! Audio generation with state-space models","author":"goel","year":"0","journal-title":"Proceedings of the 39th International Conference on Machine Learning 2022 vol 162 of Proceedings of Machine Learning Research"},{"key":"ref7","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.07.007"},{"article-title":"Chasing Carbon : The Elusive Environmental Footprint of Computing","year":"2019","author":"gupta","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i09.7123"},{"key":"ref6","first-page":"3645","article-title":"Energy and policy considerations for deep learning in NLP","author":"strubell","year":"2020","journal-title":"ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics Proceedings of the Conference"},{"article-title":"Towards the systematic reporting of the energy and carbon footprints of machine learning","year":"2020","author":"henderson","key":"ref5"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096975.pdf?arnumber=10096975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:02:05Z","timestamp":1700506925000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096975\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096975","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}