{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:13:57Z","timestamp":1776885237542,"version":"3.51.2"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11230921","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Learning Robust Spatial Representations from Binaural Audio through Feature Distillation"],"prefix":"10.1109","author":[{"given":"Holger Severin","family":"Bovbjerg","sequence":"first","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"\u00d8stergaard","sequence":"additional","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jesper","family":"Jensen","sequence":"additional","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[{"name":"Aalborg University,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1152\/physrev.00026.2009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/89.568735"},{"key":"ref4","volume-title":"Microphone Array Signal Processing","volume":"1","author":"Benesty","year":"2008"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2011.09.032"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178484"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-024-00377-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1986.1143830"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-645"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2750760"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.20965\/jrm.2017.p0037"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101360"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2919378"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3043107"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3507560"},{"key":"ref17","first-page":"28 708","article-title":"Masked autoencoders that listen","volume-title":"Proc. NeurIPS","volume":"35","author":"Huang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1473"},{"key":"ref19","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","volume":"33","author":"Baevski"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref22","article-title":"Beats: audio pre-training with acoustic tokenizers","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Chen"},{"key":"ref23","volume":"abs\/1807.03748","author":"van den Oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.570"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747379"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3264570"},{"key":"ref27","first-page":"34 021","article-title":"Unssor: Unsupervised neural speech separation by leveraging over-determined training mixtures","volume-title":"Proc. NeurIPS","volume":"36","author":"Wang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3458811"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref31","article-title":"HRTF-DATABASE","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC53105.2022.9914754"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096047"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268734"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1111"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10821"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref39","article-title":"anf-generator","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846281"},{"key":"ref41","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"Tahoe City, CA, USA","start":{"date-parts":[[2025,10,12]]},"end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11230921.pdf?arnumber=11230921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:56:51Z","timestamp":1763193411000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230921\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11230921","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}