{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:47:55Z","timestamp":1781016475227,"version":"3.54.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icasspw62465.2024.10627629","type":"proceedings-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:19:18Z","timestamp":1723742358000},"page":"590-594","source":"Crossref","is-referenced-by-count":12,"title":["Layer-Wise Analysis of Self-Supervised Acoustic Word Embeddings: A Study on Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Alexandra","family":"Saliba","sequence":"first","affiliation":[{"name":"University of Edinburgh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanchao","family":"Li","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramon","family":"Sanabria","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Catherine","family":"Lai","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCS.2011.6140822"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.894524"},{"key":"ref4","article-title":"Word-level acoustic modeling with convolutional vector regression","volume-title":"Proc. ICML Workshop Representation Learn","author":"Maas"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707765"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096099"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3083821"},{"key":"ref8","article-title":"Cross-attention is not enough: Incongruity-aware dynamic hierarchical fusion for multimodal affect recognition","author":"Wang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref10","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":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023428"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref18","article-title":"A correspondence variational autoencoder for unsupervised acoustic word embeddings","author":"Peng","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023234"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511122"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10627629.pdf?arnumber=10627629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T05:55:24Z","timestamp":1723787724000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10627629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10627629","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}