{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T08:22:01Z","timestamp":1773217321035,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683596","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"176-180","source":"Crossref","is-referenced-by-count":21,"title":["Neural Music Synthesis for Flexible Timbre Control"],"prefix":"10.1109","author":[{"given":"Jong Wook","family":"Kim","sequence":"first","affiliation":[]},{"given":"Rachel","family":"Bittner","sequence":"additional","affiliation":[]},{"given":"Aparna","family":"Kumar","sequence":"additional","affiliation":[]},{"given":"Juan Pablo","family":"Bello","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2307\/3680283"},{"key":"ref11","article-title":"Mel Frequency Cepstral Coefficients for Music Modeling","author":"logan","year":"2000","journal-title":"Proceedings of the International Society for Music Information Retrieval (ISMIR) Conference"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865703210118"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2011.105"},{"key":"ref14","article-title":"Generative Timbre Spaces with Variational Audio Synthesis","author":"esling","year":"2018","journal-title":"Proceedings of the International Conference on Digital Audio Effects (DAFx)"},{"key":"ref15","article-title":"Auto-Encoding Variational Bayes","author":"kingma","year":"2014","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref16","article-title":"WaveNet: A Generative Model for Raw Audio","author":"vanden oord","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref18","article-title":"Deep Voice 3: 2000-Speaker Neural Text-to-Speech","author":"ping","year":"2018","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref19","first-page":"70","article-title":"Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders","author":"engel","year":"2017","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref28","article-title":"Visualizing Data Using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","article-title":"Sound Morphing with Gaussian Mixture Models","author":"boccardi","year":"2001","journal-title":"Proceedings of DAFX"},{"key":"ref27","article-title":"Parallel WaveNet: Fast High-Fidelity Speech Synthesis","author":"vanden oord","year":"2017"},{"key":"ref3","article-title":"Timbre Interpolation of Sounds Using a Sinusoidal Model","author":"osaka","year":"1995","journal-title":"Proceedings of the International Computer Music Conference"},{"key":"ref6","article-title":"Morphing Spectral Envelopes using Audio Flow","author":"ezzat","year":"2005","journal-title":"European Conference on Speech Communication and Technology"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543292"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.3642604"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2260154"},{"key":"ref2","article-title":"Automatic Timbral Morphing of Musical Instrument Sounds by High-Level descriptors","author":"caetano","year":"2010","journal-title":"Proceedings of the International Computer Music Conference"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.381428"},{"key":"ref1","author":"pejrolo","year":"2017","journal-title":"Creating Sounds from Scratch A Practical Guide to Music Synthesis for Producers and Composers"},{"key":"ref20","article-title":"A Universal Music Translation Network","author":"mor","year":"2018"},{"key":"ref22","article-title":"Onsets and frames: Dual-Objective Piano Transcription","author":"hawthorne","year":"2018","journal-title":"Proceedings of the International Society for Music Information Retrieval (ISMIR) Conference"},{"key":"ref21","article-title":"Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset","year":"2019","journal-title":"Submitted to International Conference on Learning Representations (ICLR 2016)"},{"key":"ref24","article-title":"Learning Features of Music from Scratch","author":"thickstun","year":"2017","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref23","article-title":"Film: Visual Reasoning with a General Conditioning Layer","author":"perez","year":"2018","journal-title":"Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI) Conference"},{"key":"ref26","article-title":"Method for the Subjective Assessment of Intermediate Quality Level of Coding Systems","year":"2001","journal-title":"ITU-R Recommendation BS 1534-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038819"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683596.pdf?arnumber=8683596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:13:29Z","timestamp":1657854809000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683596\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683596","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}