{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:55:23Z","timestamp":1776887723599,"version":"3.51.2"},"reference-count":20,"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\/icassp49357.2023.10096066","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":5,"title":["Streaming Voice Conversion via Intermediate Bottleneck Features and Non-Streaming Teacher Guidance"],"prefix":"10.1109","author":[{"given":"Yuanzhe","family":"Chen","sequence":"first","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Tu","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tang","family":"Li","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuqiang","family":"Kong","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxin","family":"Li","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhichao","family":"Wang","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiao","family":"Tian","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuping","family":"Wang","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Speech, Audio & Music Intelligence (SAMI), ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054675"},{"key":"ref12","article-title":"Paralinguistics","year":"0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2021-14","article-title":"Delightfultts: The microsoft speech synthesis system for blizzard challenge 2021","author":"liu","year":"2021"},{"key":"ref20","first-page":"3830","article-title":"ECAPA-TDNN: Emphasized channel attention, propagation and aggregation in tdnn based speaker verification","author":"desplanques","year":"2020","journal-title":"InterSpeech"},{"key":"ref11","article-title":"Unified streaming and non-streaming two-pass end-to-end model for speech recognition","author":"zhang","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747558"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747020"},{"key":"ref1","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":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref16","article-title":"TFGAN: Time and frequency domain based generative adversarial network for high-fidelity speech synthesis","author":"tian","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1351"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref8","article-title":"FastS2S-VC: Streaming non-autoregressive sequence-to-sequence voice conversion","author":"kameoka","year":"2021"},{"key":"ref7","article-title":"Streaming non-autoregressive model for any-to-many voice conversion","author":"chen","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-25"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747625"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688277"},{"key":"ref5","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume":"34","author":"choi","year":"2021","journal-title":"Advances in Neural IInformation Processing Systems"}],"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\/10096066.pdf?arnumber=10096066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T22:07:51Z","timestamp":1729375671000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096066","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}