{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:38:46Z","timestamp":1776886726697,"version":"3.51.2"},"reference-count":29,"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\/icassp49357.2023.10096442","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["Low-Latency Electrolaryngeal Speech Enhancement Based on Fastspeech2-Based Voice Conversion and Self-Supervised Speech Representation"],"prefix":"10.1109","author":[{"given":"Kazuhiro","family":"Kobayashi","sequence":"first","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":"ref13","author":"kameoka","year":"2021","journal-title":"FastS2S-VC Streaming non-autoregressive sequence-to-sequence voice conversion"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2020EDP7252"},{"key":"ref15","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"Proc ICLR"},{"key":"ref14","author":"chen","year":"2022","journal-title":"Streaming non-autoregressive model for any-to-many voice conversion"},{"key":"ref11","first-page":"142","article-title":"Low-latency real-time non-parallel voice conversion based on cyclic variational autoencoder and multiband wavernn with data-driven linear prediction","author":"tobing","year":"2021","journal-title":"Proc SSW"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-17"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E97.D.1429"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553154"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747558"},{"key":"ref19","article-title":"Two-stage training method for japanese electrolaryngeal speech enhancement based on sequence-to-sequence voice conversion","author":"ma","year":"2021","journal-title":"Proc SLT"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687908"},{"key":"ref24","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2020","journal-title":"Proc ICLR"},{"key":"ref23","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume":"28","author":"bengio","year":"2015","journal-title":"Proc NIPS"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref20","first-page":"1","article-title":"Electrolaryngeal speech enhancement based on a two stage framework with bottleneck feature refinement and voice conversion","volume":"80","author":"yaogen","year":"2023","journal-title":"J EAMBES"},{"key":"ref22","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287721"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-29"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413973"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688277"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746430"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2977678"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2960721"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10096442.pdf?arnumber=10096442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:09:19Z","timestamp":1700507359000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096442","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}