{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T15:27:05Z","timestamp":1790090825248,"version":"4.0.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446863","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11016-11020","source":"Crossref","is-referenced-by-count":18,"title":["STREAMVC: Real-Time Low-Latency Voice Conversion"],"prefix":"10.1109","author":[{"given":"Yang","family":"Yang","sequence":"first","affiliation":[{"name":"Google LLC,U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yury","family":"Kartynnik","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunpeng","family":"Li","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiuqiang","family":"Tang","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Li","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"Sung","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Grundmann","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"ref2","article-title":"AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss","volume-title":"ICLR 2019","author":"Qian"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096066"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref9","author":"Guo","journal-title":"QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096220"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref13","article-title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","volume-title":"ICML 2021","author":"Kim"},{"key":"ref14","article-title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","author":"Kong","journal-title":"NeurIPS 2020"},{"key":"ref15","article-title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","volume-title":"NeurIPS 2019","author":"Kumar"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413439"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1003"},{"key":"ref21","article-title":"XNNPACK","author":"Dukhan"},{"key":"ref22","article-title":"Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme","volume-title":"ICLR 2022","author":"Popov"},{"key":"ref23","article-title":"Lib-riTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","volume-title":"INTERSPEECH 2019","author":"Zen"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446863.pdf?arnumber=10446863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:45:56Z","timestamp":1722573956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446863","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}