{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:25:36Z","timestamp":1776885936409,"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\/icassp49660.2025.10890041","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Investigation of Spatial Self-Supervised Learning and Its Application to Target Speaker Speech Recognition"],"prefix":"10.1109","author":[{"given":"Yoshiaki","family":"Bando","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuele","family":"Cornell","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoru","family":"Fukayama","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Proc. of Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095596"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3200911"},{"key":"ref4","first-page":"3846","article-title":"Unsupervised sound separation using mixture invariant training","volume":"33","author":"Wisdom","year":"2020","journal-title":"Proc. of Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref5","first-page":"1","article-title":"UNSSOR: Unsupervised neural speech separation by leveraging over-determined training mixtures","volume":"36","author":"Wang","year":"2024","journal-title":"Proc. of Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2549"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3101699"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683520"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054171"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054328"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-42"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760429"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2050716"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2239990"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053556"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10289974"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2024-1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287336"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11077"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3019181"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553306"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682291"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472671"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683704"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8903054"},{"key":"ref29","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013"},{"key":"ref30","first-page":"1","article-title":"The AMI meeting corpus","volume-title":"Proc. of International Conference on Methods and Techniques in Behavioral Research","author":"Kraaij"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1137"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414255"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2800"},{"key":"ref34","article-title":"The Mixer 6 corpus: Resources for cross-channel and text independent speaker recognition","volume-title":"Proc. of International Conference on Language Resources and Evaluation (LREC)","author":"Brandschain"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1788"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2210879"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.09.015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446670"}],"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\/10890041.pdf?arnumber=10890041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:24Z","timestamp":1774416384000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890041\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890041","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}