{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T02:23:22Z","timestamp":1778034202779,"version":"3.51.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"EPSRC Centre for Doctoral Training in Intelligent Games & Game Intelligence","award":["EP\/L015846\/1"],"award-info":[{"award-number":["EP\/L015846\/1"]}]},{"name":"Sony Interactive Entertainment Europe"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3364616","type":"journal-article","created":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T20:12:55Z","timestamp":1708373575000},"page":"1573-1585","source":"Crossref","is-referenced-by-count":4,"title":["NoiseBandNet: Controllable Time-Varying Neural Synthesis of Sound Effects Using Filterbanks"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7538-2793","authenticated-orcid":false,"given":"Adri\u00e1n","family":"Barahona-R\u00edos","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of York, York, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7880-5093","authenticated-orcid":false,"given":"Tom","family":"Collins","sequence":"additional","affiliation":[{"name":"Frost School of Music, University of Miami, Coral Gables, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Modern Radio and Audio Production: Programming and Performance","author":"Hausman","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2040532"},{"key":"ref3","article-title":"Post-Keynote Panel: Procedural sound synthesis for AR\/VR","year":"2023"},{"key":"ref4","volume-title":"Designing Sound","author":"Farnell","year":"2010"},{"key":"ref5","first-page":"302","article-title":"SpecSinGAN: Sound effect variation synthesis using single-image GANs","volume-title":"Proc. 19th Sound Music Comput. Conf.","author":"Barahona-Ros","year":"2022"},{"key":"ref6","article-title":"Neural synthesis of footsteps sound effects with generative adversarial networks","volume-title":"Proc. Audio Eng. Soc. Conv. 152","author":"Comunit","year":"2022"},{"key":"ref7","article-title":"DDSP: Differentiable digital signal processing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Engel","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2307\/3680788"},{"key":"ref9","first-page":"175","article-title":"Real-time timbre transfer and sound synthesis using DDSP","volume-title":"Proc. 18th Sound Music Comput. Conf.","author":"Ganis","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095188"},{"key":"ref11","article-title":"Im sorry for your loss: Spectrally-based audio distances are bad at pitch","volume-title":"Proc. I Cant Believe Its Not Better! NeurIPS Workshop","author":"Turian","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2018.0033"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2010.5444796"},{"key":"ref14","article-title":"Fxive: A web platform for procedural sound synthesis","volume-title":"Proc. AES Conv.","author":"Bahadoran","year":"2018"},{"key":"ref15","first-page":"450","article-title":"Synthesising knocking sound effects using conditional WaveGAN","volume-title":"Proc. 17th Sound Music Comput. Conf.","author":"Barahona-Ros","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596430"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096760"},{"key":"ref18","article-title":"AudioGen: Textually guided audio generation","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Kreuk","year":"2023"},{"key":"ref19","first-page":"21450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Liu","year":"2023"},{"key":"ref20","first-page":"20916","article-title":"Catch-a-Waveform: Learning to generate audio from a single short example","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Greshler","year":"2021"},{"key":"ref21","first-page":"403","article-title":"Sonifying energy consumption using SpecSinGAN","volume-title":"Proc. 20th Sound Music Comput. Conf.","author":"Pauletto","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v18i1.21941"},{"key":"ref23","first-page":"254","article-title":"Neural waveshaping synthesis","volume-title":"Proc. 22nd Int. Soc. \n Music Inf. Retrieval Conf.","author":"Hayes","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746940"},{"key":"ref25","first-page":"608","article-title":"DDX7: Differentiable FM synthesis of musical instrument sounds","volume-title":"Proc. 23rd Int. Soc. Music Inf. Retrieval Conf.","author":"Caspe","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095139"},{"key":"ref27","article-title":"Data-driven procedural audio: Procedural engine sounds using neural audio synthesis","author":"Lundberg","year":"2020"},{"key":"ref28","article-title":"A neural analysissynthesis approach to learning procedural audio models","author":"Serrano","year":"2022"},{"key":"ref29","first-page":"590","article-title":"DrumGAN: Synthesis of drum sounds with timbral feature conditioning using generative adversarial networks","volume-title":"Proc. 21st Int. Soc. Music Inf. Retrieval Conf.","author":"Nistal","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000049"},{"key":"ref31","article-title":"RAVE: A. variational autoencoder for fast and high-quality neural audio synthesis","author":"Caillon","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-03789-4_20"},{"key":"ref34","article-title":"Raw music from free movements: Early experiments in using machine learning to create raw audio from dance movements","volume-title":"Proc. 2nd Conf. AI Music Creativity","author":"Bisig","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/app10010302"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2011.06.032"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-psych-122216-011635"},{"key":"ref38","first-page":"32","article-title":"Creating endless sounds","volume-title":"Proc. Digit. Audio Effects Conf.","author":"Vlimki","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.4324\/9781315657813"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref43","article-title":"Auraloss: Audio-focused loss functions in PyTorch","volume-title":"Proc. Digit. Music Res. Netw. One-day Workshop","author":"Steinmetz","year":"2020"},{"key":"ref44","first-page":"76","article-title":"DDSP-Based singing vocoders: A new subtractive-based synthesizer and a comprehensive evaluation","volume-title":"Proc. ISMIR Hybrid Conf.","author":"Wu","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2219"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.4324\/9781351016438"},{"key":"ref47","first-page":"280","article-title":"Differentiable time-frequency scattering on GPU","volume-title":"Proc. Digit. Audio Effects Conf.","author":"Muradeli","year":"2022"},{"key":"ref48","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"key":"ref49","article-title":"Efficient neural networks for realtime modeling of analog dynamic range compression","volume-title":"Proc. Audio Eng. Soc. Conv. 152","author":"Steinmetz","year":"2022"},{"key":"ref50","article-title":"Auto-encoding variational bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref51","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende","year":"2014"},{"key":"ref52","article-title":"High fidelity neural audio compression","author":"Dfossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054708"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10440034.pdf?arnumber=10440034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T02:09:56Z","timestamp":1709863796000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10440034\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3364616","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}