{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:15:03Z","timestamp":1776885303639,"version":"3.51.2"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889792","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Aligning Noisy-Clean Speech Pairs at Feature and Embedding Levels for Learning Noise-Invariant Speaker Representations"],"prefix":"10.1109","author":[{"given":"Zuoliang","family":"Li","sequence":"first","affiliation":[{"name":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Ai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengyu","family":"Peng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Guan","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Gu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3313431"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3231709"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3136141"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1558"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-973"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053110"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3039930"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3304474"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3290832"},{"key":"ref14","author":"Song","year":"2020","journal-title":"Score-based generative modeling through stochastic differential equations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446375"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053407"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2894"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref19","first-page":"18 661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"12 310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"International conference on machine learning","author":"Zbontar"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref23","first-page":"807","article-title":"Rectified linear units improve restricted boltz-mann machines","volume-title":"Proceedings of the 27th international conference on machine learning (ICML-10)","author":"Nair"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3244428"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1496"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1978"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096848"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-155"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-700"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1106"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11301"},{"key":"ref33","author":"Snyder","year":"2015","journal-title":"Musan: A music, speech, and noise corpus"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041110"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref36","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"issue":"11","key":"ref38","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889792.pdf?arnumber=10889792","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:29Z","timestamp":1774416329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889792\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889792","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}