{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:42:13Z","timestamp":1776879733610,"version":"3.51.2"},"reference-count":21,"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\/icassp49357.2023.10096670","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["Continuous Descriptor-Based Control for Deep Audio Synthesis"],"prefix":"10.1109","author":[{"given":"Ninon","family":"Devis","sequence":"first","affiliation":[{"name":"IRCAM - Sorbonne Université, CNRS UMR 9912,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nils","family":"Demerl\u00e9","sequence":"additional","affiliation":[{"name":"IRCAM - Sorbonne Université, CNRS UMR 9912,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarah","family":"Nabi","sequence":"additional","affiliation":[{"name":"IRCAM - Sorbonne Université, CNRS UMR 9912,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Genova","sequence":"additional","affiliation":[{"name":"IRCAM - Sorbonne Université, CNRS UMR 9912,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philippe","family":"Esling","sequence":"additional","affiliation":[{"name":"IRCAM - Sorbonne Université, CNRS UMR 9912,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Ddsp: Differentiable digital signal processing","author":"engel","year":"2020"},{"key":"ref12","article-title":"Durian: Duration informed attention network for multimodal synthesis","author":"yu","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00789"},{"key":"ref14","article-title":"Geometric gan","author":"lim","year":"2017"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref11","article-title":"Attributes-aware deep music transformation","author":"kawai","year":"2020","journal-title":"Proceedings of the 21st international society for music information retrieval conference ismir"},{"key":"ref10","article-title":"Fader networks: Manipulating images by sliding attributes","volume":"30","author":"lample","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1191"},{"key":"ref2","article-title":"Diet deep generative audio models with structured lottery","author":"esling","year":"2020"},{"key":"ref1","article-title":"Samplernn: An un-conditional end-to-end neural audio generation model","author":"mehri","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.3642604"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916751"},{"key":"ref19","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018"},{"key":"ref18","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"engel","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref9","article-title":"Learning structured output representation using deep conditional generative models","volume":"28","author":"sohn","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"RAVE: A variational autoencoder for fast and high-quality neural audio synthesis","author":"caillon","year":"2021","journal-title":"CoRR"},{"key":"ref5","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10096670.pdf?arnumber=10096670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:07:49Z","timestamp":1700489269000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096670\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096670","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}