{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:16:30Z","timestamp":1776885390238,"version":"3.51.2"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462431","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"2251-2255","source":"Crossref","is-referenced-by-count":60,"title":["Fftnet: A Real-Time Speaker-Dependent Neural Vocoder"],"prefix":"10.1109","author":[{"given":"Zeyu","family":"Jin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Finkelstein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gautham J.","family":"Mysore","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingwan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5594\/J10096"},{"key":"ref11","first-page":"iv","article-title":"Statistical parametric speech synthesis","volume":"4","author":"black","year":"2007","journal-title":"Proc ICASSP"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/ecja.4400660203"},{"key":"ref13","author":"paine","year":"2016","journal-title":"Fast WaveNet generation algorithm"},{"key":"ref14","author":"arik","year":"2017","journal-title":"Deep Voice Real-time neural text-to-speech"},{"key":"ref15","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","volume":"abs 1711 10433","author":"van den oord","year":"2017","journal-title":"CoRR"},{"key":"ref16","first-page":"1","article-title":"Voice conversion: A critical survey","author":"machado","year":"2010","journal-title":"Proc Sound and Music Computing (SMC)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1965-0178586-1"},{"key":"ref18","first-page":"4790","article-title":"Conditional image generation with pixelcnn decoders","author":"van den oord","year":"2016","journal-title":"NIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref4","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"ICLR 2017 workshop"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40585-3_30"},{"key":"ref3","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","volume":"abs 1703 10135","author":"wang","year":"2017","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.21437\/Interspeech.2017-986","article-title":"Statistical voice conversion with wavenet-based waveform generation","author":"kobayashi","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref5","author":"ramos","year":"2016","journal-title":"Voice conversion with deep learning"},{"key":"ref8","author":"engel","year":"2017","journal-title":"Neural audio synthesis of musical notes with wavenet autoencoders"},{"key":"ref7","article-title":"A wavenet for speech denoising","volume":"abs 1706 7162","author":"rethage","year":"2017","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-5730-8"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.21437\/Interspeech.2017-314","article-title":"Speaker-dependent wavenet vocoder","author":"tamamori","year":"2017","journal-title":"Proceedings of Interspeech"},{"key":"ref1","author":"van den oord","year":"2016","journal-title":"WaveNet A Generative Model for Raw Audio"},{"key":"ref20","article-title":"The cmu arctic speech databases","author":"kominek","year":"2004","journal-title":"Proc Fifth ISCA Speech Synthesis Workshop"},{"key":"ref22","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/1745691610393980"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"96: 1","DOI":"10.1145\/3072959.3073702","article-title":"Voco: Text-based insertion and replacement in audio narration","volume":"36","author":"jin","year":"2017","journal-title":"ACM Trans Graph"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/9781118541241"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471749"},{"key":"ref25","first-page":"5660","article-title":"Cute: A concatenative method for voice conversion using exemplar-based unit selection","author":"jin","year":"2016","journal-title":"Proc ICASSP"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462431.pdf?arnumber=8462431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T05:18:37Z","timestamp":1598246317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462431","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}