{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:22Z","timestamp":1764399082741,"version":"3.46.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249126","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"589-594","source":"Crossref","is-referenced-by-count":0,"title":["Interpolating Speaker Identities in Embedding Space for Data Expansion"],"prefix":"10.1109","author":[{"given":"Tianchi","family":"Liu","sequence":"first","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruijie","family":"Tao","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiongqiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I R), Agency for Science, Technology and Research (A*STAR),Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yidi","family":"Jiang","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hardik B.","family":"Sailor","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I R), Agency for Science, Technology and Research (A*STAR),Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Zhang","sequence":"additional","affiliation":[{"name":"SRIBD, School of Artificial Intelligence, The Chinese University of Hong Kong,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingru","family":"Lin","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"SRIBD, School of Artificial Intelligence, The Chinese University of Hong Kong,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2116"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3385277"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10887949"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889058"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3143036"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1490"},{"key":"ref8","article-title":"3dspeaker: A large-scale multi-device, multi-distance, and multidialect corpus for speech representation disentanglement","author":"Zheng","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3492793"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446513"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1508"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3016498"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889137"},{"key":"ref16","article-title":"Libri2Vox dataset: Target speaker extraction with diverse speaker conditions and synthetic data","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1882"},{"key":"ref18","article-title":"Voice conversion augmentation for speaker recognition on defective datasets","author":"Tao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414438"},{"key":"ref20","first-page":"50221","article-title":"Disentangling voice and content with self-supervision for speaker recognition","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747162"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3039573"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/325165.325242"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-715"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref29","first-page":"27403","article-title":"Darpa timit acoustic-phonetic continous speech corpus cdrom. nist speech disc 1\u20131.1","volume":"93","author":"Garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report N"},{"key":"ref30","first-page":"995","article-title":"Samr\u00f3mur children: An Icelandic speech corpus","volume-title":"Proc. LREC","author":"Mena","year":"2022"},{"key":"ref31","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. ICML","author":"Casanova","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2650"},{"key":"ref35","article-title":"The speakin system for voxceleb speaker recognition challange 2021","author":"Zhao","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832142"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3091932"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249126.pdf?arnumber=11249126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:10Z","timestamp":1764399010000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249126","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}