{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T21:31:37Z","timestamp":1729632697003,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639608","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"297-303","source":"Crossref","is-referenced-by-count":5,"title":["An Evaluation of Deep Spectral Mappings and WaveNet Vocoder for Voice Conversion"],"prefix":"10.1109","author":[{"given":"Patrick Lumban","family":"Tobing","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Chiao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"3067","article-title":"A hybrid approach to electrolaryngeal speech enhancement based on spectral subtraction and statistical voice conversion","author":"tanaka","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2753583"},{"key":"ref12","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref13","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":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref15","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"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462393"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-31"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref4","article-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","author":"kaneko","year":"2017","journal-title":"arXiv preprint arXiv 1711 11585"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2593263"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.011"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"2162","DOI":"10.21437\/Interspeech.2010-596","article-title":"Applying voice conversion to concatenative singing-voice synthesis","author":"villavicencio","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205241"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.09.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref20","article-title":"Natural TTS synthesis by conditioning WaveNet on mel spectrogram predictions","author":"shen","year":"2017","journal-title":"CoRR"},{"journal-title":"Python-Wrapper-for-World-Vocoder","year":"0","author":"hsu","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref24","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"AISTATS"},{"year":"0","author":"hayashi","key":"ref23"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"CoRR"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2018,12,18]]},"location":"Athens, Greece","end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639608.pdf?arnumber=8639608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T17:14:29Z","timestamp":1694625269000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639608","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}