{"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":1776879752986,"version":"3.51.2"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3237161","type":"journal-article","created":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T19:23:54Z","timestamp":1673897034000},"page":"863-875","source":"Crossref","is-referenced-by-count":9,"title":["Improving Semi-Supervised Differentiable Synthesizer Sound Matching for Practical Applications"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8064-3038","authenticated-orcid":false,"given":"Naotake","family":"Masuda","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Information Systems, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daisuke","family":"Saito","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Information Systems, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2783885"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/app10010302"},{"key":"ref3","first-page":"428","article-title":"Synthesizer sound matching with differentiable DSP","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf","author":"Masuda","year":"2021"},{"key":"ref4","article-title":"DDSP: Differentiable digital signal processing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Engel","year":"2020"},{"key":"ref5","first-page":"363","article-title":"SynthAssist: Querying an audio synthesizer by vocal imitation","volume-title":"Proc. Int. Conf. New Interfaces For Musical Expression","author":"Cartwright","year":"2014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2265086"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2307\/3680541"},{"key":"ref8","first-page":"33","article-title":"Automated optimization of parameters for FM sound synthesis with genetic algorithms","volume-title":"Proc. Workshop Comput. Music Audio Technol","author":"Lai","year":"2006"},{"key":"ref9","article-title":"Automatic calibration of modified FM synthesis to harmonic sounds using genetic algorithms","volume-title":"Proc. 9th Sound Music Comput. Conf","author":"Macret","year":"2012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865703302100"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/DAFx51585.2021.9768271"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2016.1175481"},{"key":"ref13","first-page":"1426","article-title":"Parameter estimation of virtual musical instrument synthesizers","volume-title":"Proc. 40th Int. Comput. Music Conf","author":"Itoyama","year":"2014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2944568"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851950"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1121\/10.0005622"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415103"},{"key":"ref18","first-page":"9041","article-title":"SING: Symbol-to-instrument neural generator","volume-title":"Proc. Adv. Neural Inf., Process. Syst","author":"Dfossez","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683596"},{"key":"ref20","first-page":"1411","article-title":"Musical audio synthesis using autoencoding neural nets","volume-title":"Proc. Int. Comput. Music Conf.","author":"Sarroff","year":"2014"},{"key":"ref21","first-page":"1068","article-title":"Neural audio synthesis of musical notes with WaveNet autoencoders","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Engel","year":"2017"},{"key":"ref22","article-title":"RAVE: A variational autoencoder for fast and high-quality neural audio synthesis","author":"Caillon","year":"2021"},{"key":"ref23","first-page":"91","article-title":"Musical sound modeling with sinusoids plus noise","volume-title":"Musical Signal Processing","author":"Serra","year":"1997"},{"key":"ref24","first-page":"916","article-title":"Hierarchical timbre-painting and articulation generation","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Michelashvili"},{"key":"ref25","article-title":"Self-supervised pitch detection by inverse audio synthesis","volume-title":"Proc. Workshop Self-Supervision Audio Speech 37th Int. Conf. Mach. Learn.","author":"Engel","year":"2020"},{"key":"ref26","first-page":"254","article-title":"Neural waveshaping synthesis","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Hayes","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746940"},{"key":"ref28","first-page":"297","article-title":"Differentiable IIR filters for machine learning applications","volume-title":"Proc. Int. Conf. Digit. Audio Effects","author":"Kuznetsov","year":"2020"},{"key":"ref29","first-page":"265","article-title":"Neural parametric equalizer matching using differentiable biquads","volume-title":"Proc. Int. Conf. Digit. Audio Effects","author":"Nercessian","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00411"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01543"},{"key":"ref32","first-page":"1887","article-title":"3D-aware scene manipulation via inverse graphics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yao","year":"2018"},{"key":"ref33","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jaderberg","year":"2015"},{"key":"ref34","article-title":"Im sorry for your loss: Spectrally-based audio distances are bad at pitch","volume-title":"Proc. 1st I. Cant Believe Its Not Better Workshop","author":"Turian","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05855-6"},{"key":"ref37","first-page":"63","article-title":"Synthesizer voice quality of new languages","volume-title":"Proc. Workshop Spoken Lang. Technol. Under-Resourced Lang.","author":"Kominek","year":"2008"},{"key":"ref38","first-page":"61","article-title":"Perceptual distance in timbre space","volume-title":"Proc. 11th Meeting Int. Conf. Auditory Display","volume":"5","author":"Terasawa","year":"2005"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref41","article-title":"Envelope model of isolated musical sounds","volume-title":"Proc. 2nd COST G-6 Workshop Digit. Audio Effects","author":"Jensen","year":"1999"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3400066"},{"issue":"59","key":"ref43","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.23919\/DAFx51585.2021.9768218"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10017350.pdf?arnumber=10017350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T05:53:58Z","timestamp":1707803638000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10017350\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3237161","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}