{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T10:34:36Z","timestamp":1770287676512,"version":"3.49.0"},"reference-count":20,"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.2019.8682656","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"6840-6844","source":"Crossref","is-referenced-by-count":21,"title":["Data Efficient Voice Cloning for Neural Singing Synthesis"],"prefix":"10.1109","author":[{"given":"Merlijn","family":"Blaauw","sequence":"first","affiliation":[]},{"given":"Jordi","family":"Bonada","sequence":"additional","affiliation":[]},{"given":"Ryunosuke","family":"Daido","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref11","first-page":"1118","article-title":"Speaker-dependent WaveNet vocoder","author":"tamamori","year":"2017","journal-title":"Proceedings of the 18th Annual Conference of the International Speech Communication Association (In-terspeech)"},{"key":"ref12","article-title":"Char2Wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref13","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"Advances in Neural Information Processing Systems I (NIPS)"},{"key":"ref14","author":"lorenzo-trueba","year":"2018","journal-title":"Robust universal neural vocoding"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694316"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref18","article-title":"VoiceLoop: Voice fitting and synthesis via a phonological loop","author":"taigman","year":"2018","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref19","first-page":"3683","article-title":"Fitting new speakers based on a short untranscribed sample","author":"nachmani","year":"2018","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref4","article-title":"Performance-driven control for sample-based singing voice synthesis","author":"janer","year":"2006","journal-title":"Proc Int Conf Digital Audio Effects (DAFx)"},{"key":"ref3","article-title":"A neural parametric singing synthesizer modeling timbre and expression from natural songs","volume":"7","author":"blaauw","year":"1313","journal-title":"Applied Sciences"},{"key":"ref6","article-title":"Modeling singing F0 with neural network driven transition-sustain models","author":"hua","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2424572"},{"key":"ref8","article-title":"Neural voice cloning with a few samples","author":"arik","year":"2018","journal-title":"Advances in Neural Information Processing Systems I (NIPS)"},{"key":"ref7","first-page":"2962","article-title":"Deep Voice 2: Multi-speaker neural text-to-speech","author":"arik","year":"2017","journal-title":"Advances in Neural Information Processing Systems I (NIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref9","article-title":"Sample efficient adaptive text-to-speech","author":"chen","year":"2019","journal-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854062"}],"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\/08682656.pdf?arnumber=8682656","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:23:04Z","timestamp":1657855384000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682656\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682656","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}