{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T04:47:45Z","timestamp":1763959665011,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413959","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"5934-5938","source":"Crossref","is-referenced-by-count":11,"title":["Crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational Autoencoder"],"prefix":"10.1109","author":[{"given":"Kazuhiro","family":"Kobayashi","sequence":"first","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Chin","family":"Huang","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Chiao","family":"Wu","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick Lumban","family":"Tobing","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier gans","volume":"70","author":"odena","year":"2017","journal-title":"Proc MLRE"},{"article-title":"Generating diverse high-fidelity images with VQ-VAE-2","year":"2019","author":"razavi","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-879"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2977678"},{"key":"ref11","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Proc NIPS"},{"key":"ref12","first-page":"724","article-title":"Group Latent Embedding for Vector Quantized Variational Autoencoder in Non-Parallel Voice Conversion","author":"shaojin","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-20"},{"article-title":"The NeteaseGames system for voice conversion challenge 2020 with vector-quantization variational autoencoder and WaveNet","year":"2020","author":"haitong","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462342"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref28","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"article-title":"Voice Transformer Network: Sequence-to-sequence voice conversion using transformer with text-to-speech pretraining","year":"2019","author":"huang","key":"ref4"},{"article-title":"Voice Conversion Challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion","year":"2020","author":"zhao","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.09.003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2960721"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2917232"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2307"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2014.7032186"},{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref20"},{"article-title":"Festvox: Tools for creation and analyses of large speech corpora","year":"2011","author":"anumanchipalli","key":"ref22"},{"article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","year":"2013","author":"bengio","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-33"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-29"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"195","DOI":"10.21437\/Odyssey.2018-28","article-title":"The Voice Conversion Challenge 2018: Promoting development of parallel and nonparallel methods","author":"trueba","year":"2018","journal-title":"Proc Odyssey"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-23"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413959.pdf?arnumber=9413959","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T20:20:02Z","timestamp":1659471602000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413959\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413959","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}