{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:10:26Z","timestamp":1776885026693,"version":"3.51.2"},"reference-count":40,"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\/apsipaasc65261.2025.11249009","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"2529-2534","source":"Crossref","is-referenced-by-count":1,"title":["Voice Conversion Augmentation for Speaker Recognition on Defective Datasets"],"prefix":"10.1109","author":[{"given":"Ruijie","family":"Tao","sequence":"first","affiliation":[{"name":"National University of Singapore,Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhan","family":"Shi","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, School of Artificial Intelligence,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yidi","family":"Jiang","sequence":"additional","affiliation":[{"name":"National University of Singapore,Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianchi","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Singapore,Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Singapore,Electrical and Computer Engineering,Singapore"}],"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":"10.1006\/dspr.1999.0361"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101058"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1513"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3143036"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1129"},{"key":"ref11","article-title":"Disentangling voice and content with self-supervision for speaker recognition","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747162"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3331949"},{"key":"ref14","first-page":"1641","article-title":"Semi-supervised contrastive learning with generalized contrastive loss and its application to speaker recognition","volume-title":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","author":"Inoue"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371802"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-021-01649-6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1440"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3200479"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094698"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383525"},{"key":"ref21","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"International Conference on Machine Learning (ICML)","author":"Popov"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414550"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"ref24","article-title":"Learning with noisy labels","volume":"26","author":"Natarajan","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683746"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-2401-1_21"},{"key":"ref29","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"International Conference on Learning Representations (ICLR)","author":"Popov"},{"key":"ref30","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-12616-5_4"},{"key":"ref32","volume-title":"MUSAN: A music, speech, and noise corpus","volume":"abs\/1510.08484","author":"Snyder","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2441"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1508"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2012.232"},{"issue":"1","key":"ref37","first-page":"25","article-title":"Handling imbalanced datasets: A review","volume":"30","author":"Kotsiantis","year":"2006","journal-title":"GESTS international transactions on computer science and engineering"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1064"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-126"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Singapore, Singapore","start":{"date-parts":[[2025,10,22]]},"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\/11249009.pdf?arnumber=11249009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:49:59Z","timestamp":1764398999000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249009\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249009","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}