{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:01Z","timestamp":1775229901350,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747558","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6802-6806","source":"Crossref","is-referenced-by-count":8,"title":["An Investigation of Streaming Non-Autoregressive sequence-to-sequence Voice Conversion"],"prefix":"10.1109","author":[{"given":"Tomoki","family":"Hayashi","sequence":"first","affiliation":[{"name":"TARVO Inc.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"TARVO Inc.,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":"ref10","article-title":"FastSpeech 2: Fast and high-quality end-to-end text-to-speech","author":"ren","year":"2020","journal-title":"arXiv preprint arXiv 2006 04989"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-34"},{"key":"ref13","first-page":"93","article-title":"Implementation of dnn-based real-time voice conversion and its improvements by audio data augmentation and mask-shaped device","author":"arakawa","year":"2019","journal-title":"Proc Speech Synthesis Workshop (SSW)"},{"key":"ref14","first-page":"1021","article-title":"Real-time, full-band, online dnn-based voice conversion system using a single cpu","author":"saeki","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-25"},{"key":"ref16","article-title":"Dual-mode asr: Unify and improve streaming asr with full-context modeling","author":"yu","year":"2020","journal-title":"arXiv preprint arXiv 2010 00170"},{"key":"ref17","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"arXiv preprint arXiv 2010 00170"},{"key":"ref18","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proc Advances in neural information processing systems (NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682380"},{"key":"ref3","article-title":"ConvS2S-VC: Fully convolutional sequence-to-sequence voice conversion","author":"kameoka","year":"2018","journal-title":"arXiv preprint arXiv 1811 01609"},{"key":"ref6","article-title":"Many-to-many voice transformer network","author":"kameoka","year":"2020","journal-title":"arXiv preprint arXiv 2005 06138"},{"key":"ref5","article-title":"Voice transformer network: Sequence-to-sequence voice conversion using transformer with text-to-speech pretraining","author":"huang","year":"2019","journal-title":"arXiv preprint arXiv 1912 06813"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"2514","DOI":"10.21437\/Interspeech.2014-539","article-title":"Statistical singing voice conversion with direct waveform modification based on the spectrum differential","author":"kobayashi","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413973"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-2007-11508"},{"key":"ref21","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref23","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","author":"maekawa","year":"2003","journal-title":"Proc Workshop on Spontaneous Speech Processing and Recognition"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-15"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747558.pdf?arnumber=9747558","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T03:25:30Z","timestamp":1727061930000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747558\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747558","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}