{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:42:32Z","timestamp":1776879752892,"version":"3.51.2"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T00:00:00Z","timestamp":1631059200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T00:00:00Z","timestamp":1631059200000},"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":[[2021,9,8]]},"DOI":"10.23919\/dafx51585.2021.9768246","type":"proceedings-article","created":{"date-parts":[[2022,5,11]],"date-time":"2022-05-11T16:33:41Z","timestamp":1652286821000},"page":"222-229","source":"Crossref","is-referenced-by-count":15,"title":["One Billion Audio Sounds from GPU-Enabled Modular Synthesis"],"prefix":"10.23919","author":[{"given":"Joseph","family":"Turian","sequence":"first","affiliation":[{"name":"Spooky Audio,Berlin,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jordie","family":"Shier","sequence":"additional","affiliation":[{"name":"Computer Science and Music Technology, University of Victoria,Victoria,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Tzanetakis","sequence":"additional","affiliation":[{"name":"Computer Science and Music Technology, University of Victoria,Victoria,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kirk","family":"McNally","sequence":"additional","affiliation":[{"name":"Computer Science and Music Technology, University of Victoria,Victoria,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max","family":"Henry","sequence":"additional","affiliation":[{"name":"Music Technology Area McGill University,Montreal,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Neural percussive synthesis parametrerised by high-level timbral features","author":"ramires","year":"2020","journal-title":"ICASSP"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.89.4.305"},{"key":"ref32","article-title":"A theoretical analysis of NDCG type ranking mea-sures","author":"wang","year":"0","journal-title":"COLT"},{"key":"ref31","article-title":"auraloss: Audio focused loss functions in PyTorch","author":"steinmetz","year":"2020","journal-title":"DMRN+15"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref37","article-title":"A kernel two-sample test","author":"gretton","year":"2012","journal-title":"JMLR"},{"key":"ref36","article-title":"Neu-ral granular sound synthesis","volume":"abs 2008 1393","author":"bitton","year":"2020","journal-title":"CoRR"},{"key":"ref35","article-title":"Par-allel wavegan: A fast waveform generation model based on generative adversarial networks with multi-resolution spec-trogram","author":"yamamoto","year":"2020","journal-title":"ICASSP"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref10","article-title":"YFCC100M: The new data in multimedia re-search","author":"bart","year":"2016","journal-title":"Communications of the ACM"},{"key":"ref40","article-title":"A differentiable perceptual audio metric learned from just no-ticeable differences","author":"pranay","year":"2020","journal-title":"InterSpeech"},{"key":"ref11","article-title":"Libri-light: A benchmark for asr with limited or no super-vision","author":"kahn","year":"2020","journal-title":"ICASSP"},{"key":"ref12","article-title":"The Million Song Dataset","author":"bertin-mahieux","year":"2011","journal-title":"ISMIR"},{"key":"ref13","article-title":"Jukebox: A gener-ative model for music","author":"dhariwal","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref16","article-title":"Coala: Co-aligned autoencoders for learning semantically enriched audio representations","author":"favory","year":"0","journal-title":"ICML Workshop on Self-supervision in Audio and Speech"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref18","article-title":"A crit-ical analysis of synthesizer user interfaces for timbre","author":"seago","year":"2004","journal-title":"BCS HCI"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2307\/3680541"},{"key":"ref28","article-title":"The synthesis of complex audio spectra by means of frequency modulation","author":"chowning","year":"1973","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref4","article-title":"FSD50K: an open dataset of human-labeled sound events","author":"fonseca","year":"2020","journal-title":"CoRR vol abs\/2010 00475"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1121\/1.381428"},{"key":"ref3","article-title":"Universal au-dio synthesizer control with normalizing flows","author":"masuda","year":"2019","journal-title":"DAFx"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/DAFx51585.2021.9768241"},{"key":"ref29","article-title":"I'm sorry for your loss: Spectrally-based audio distances are bad at pitch","author":"turian","year":"2020","journal-title":"ICBINB NeurIPS"},{"key":"ref5","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"engel","year":"2017","journal-title":"ICML PMLR"},{"key":"ref8","year":"2017","journal-title":"DAMP-VPB Digital Archive of Mobile Per-formances - Smule Vocal Performances Balanced"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref2","article-title":"Language models are few-shot learn-ers","author":"tom","year":"2020","journal-title":"NeuroIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref1","article-title":"Large language models in machine trans-lation","author":"thorsten","year":"2007","journal-title":"EMNLP-CoNLL"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2783885"},{"key":"ref22","article-title":"La-tent timbre synthesis","author":"tatar","year":"2020","journal-title":"Neural Computing and Applications"},{"key":"ref21","article-title":"DDSP: Differentiable digital signal processing","author":"engel","year":"2020","journal-title":"ICLRE"},{"key":"ref24","article-title":"Timbre space representation of a sub-tractive synthesizer","author":"vahidi","year":"2020","journal-title":"Timbre 2020"},{"key":"ref23","article-title":"Enabling factorized piano music modeling and generation with the maestro dataset","author":"hawthorne","year":"2019","journal-title":"ICLRE"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref25","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"ICML"}],"event":{"name":"2021 24th International Conference on Digital Audio Effects (DAFx)","location":"Vienna, Austria","start":{"date-parts":[[2021,9,8]]},"end":{"date-parts":[[2021,9,10]]}},"container-title":["2021 24th International Conference on Digital Audio Effects (DAFx)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9768159\/9768211\/09768246.pdf?arnumber=9768246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T16:11:46Z","timestamp":1656951106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9768246\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,8]]},"references-count":40,"URL":"https:\/\/doi.org\/10.23919\/dafx51585.2021.9768246","relation":{},"subject":[],"published":{"date-parts":[[2021,9,8]]}}}