{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:03:49Z","timestamp":1761897829857,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096901","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["JSV-VC: Jointly Trained Speaker Verification and Voice Conversion Models"],"prefix":"10.1109","author":[{"given":"Shogo","family":"Seki","sequence":"first","affiliation":[{"name":"NTT Corporation,NTT Communication Science Laboratories,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirokazu","family":"Kameoka","sequence":"additional","affiliation":[{"name":"NTT Corporation,NTT Communication Science Laboratories,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kou","family":"Tanaka","sequence":"additional","affiliation":[{"name":"NTT Corporation,NTT Communication Science Laboratories,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuhiro","family":"Kaneko","sequence":"additional","affiliation":[{"name":"NTT Corporation,NTT Communication Science Laboratories,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047262"},{"key":"ref35","first-page":"6547","article-title":"DGC-Vector: A New Speaker Embedding for Zero-Shot Voice Conversion","author":"xiao","year":"2022","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049336"},{"key":"ref34","first-page":"5954","article-title":"Again-VC: A One-Shot Voice Conversion Using Activation Guidance and Adaptive Instance Normalization","author":"chen","year":"2021","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref15","first-page":"1","article-title":"Auto-Encoding Variational Bayes","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations"},{"key":"ref37","first-page":"6199","article-title":"Parallel WaveGAN: A Fast Waveform Generation Model Based on Generative Adversarial Networks with Multi-Resolution Spectrogram","author":"yamamoto","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref14","first-page":"1","article-title":"Generative Adversarial Nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref36","first-page":"4879","article-title":"Generalized End-to-End Loss for Speaker Verification","author":"wan","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2307"},{"key":"ref30","first-page":"5934","article-title":"crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational Autoencoder","author":"kobayashi","year":"2021","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001456"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref10","first-page":"6805","article-title":"ATTS2S-VC: Sequence-to-sequence Voice Conversion with Attention and Context Preservation Mechanisms","author":"tanaka","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref32","first-page":"5210","article-title":"AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss","author":"qian","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WNYIPW.2019.8923082"},{"key":"ref1","first-page":"285","article-title":"Spectral voice conversion for text-to-speech synthesis","author":"kain","year":"1998","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref17","first-page":"2100","article-title":"CycleGAN-VC: Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks","author":"kaneko","year":"2018","journal-title":"European Signal Processing Conference"},{"key":"ref39","first-page":"223","article-title":"The CMU Arctic speech databases","author":"kominek","year":"2004","journal-title":"ISCA Speech Synthesis Workshop"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref38","first-page":"17022","article-title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","author":"kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"2017","article-title":"CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Melspectrogram Conversion","author":"kaneko","year":"2020","journal-title":"InterSpeech"},{"key":"ref18","first-page":"6820","article-title":"CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion","author":"kaneko","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3036784"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref25","first-page":"3581","article-title":"Semi-Supervised Learning with Deep Generative Models","author":"kingma","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"5919","article-title":"MaskCycleGAN-VC: Learning Non-Parallel Voice Conversion with Filling in Frames","author":"kaneko","year":"2021","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref41","first-page":"1","article-title":"Adam: A Method for Stochastic Gradient Optimization","author":"kingma","year":"2015","journal-title":"International Conference on Leanrning Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706604"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2917232"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041699"},{"key":"ref9","first-page":"4869","article-title":"Voice conversion using deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks","author":"sun","year":"2015","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref40","first-page":"1243","article-title":"Convolutional Sequence to Sequence Learning","author":"gehring","year":"2017","journal-title":"International Conference on Machine Learning"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096901.pdf?arnumber=10096901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:59:57Z","timestamp":1699883997000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096901\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096901","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}