{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T15:17:12Z","timestamp":1761664632686,"version":"3.37.3"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icasspw59220.2023.10193460","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:54Z","timestamp":1690997454000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Phone and Speaker Spatial Organization in Self-Supervised Speech Representations"],"prefix":"10.1109","author":[{"given":"Pablo","family":"Riera","sequence":"first","affiliation":[{"name":"Instituto de Investigación en Ciencias de la Computación (ICC), CONICET-UBA,Argentina"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuela","family":"Cerdeiro","sequence":"additional","affiliation":[{"name":"Instituto de Investigación en Ciencias de la Computación (ICC), CONICET-UBA,Argentina"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonardo","family":"Pepino","sequence":"additional","affiliation":[{"name":"Instituto de Investigación en Ciencias de la Computación (ICC), CONICET-UBA,Argentina"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luciana","family":"Ferrer","sequence":"additional","affiliation":[{"name":"Universidad de Buenos Aires (UBA),Departamento de Computación, FCEyN,Argentina"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100616"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414776"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-373"},{"key":"ref4","article-title":"What all do audio transformer models hear? probing acoustic representations for language delivery and its structure","author":"Shah","year":"2021","journal-title":"arXiv preprint arXiv:2101.00387"},{"key":"ref5","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"in International Conference on Machine Learning. PMLR","author":"Kornblith"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414321"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-441"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2362"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-304"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref12","article-title":"Decoar 2.0: Deep contextualized acoustic representations with vector quantization","author":"Ling","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref15","first-page":"12 449","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":"ref16","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"ref18","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv preprint arXiv:1611.01144"},{"article-title":"The kaldi speech recognition toolkit","volume-title":"in IEEE 2011 workshop on automatic speech recognition and understanding, no. CONF. IEEE Signal Processing Society","author":"Povey","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"ref21","first-page":"848","article-title":"Optimizing classifier performance via an approximation to the wilcoxon-mann-whitney statistic","volume-title":"in Proceedings of the 20th international conference on machine learning (icml-03)","author":"Yan"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmva.2022.104946"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1110"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/9781119808411"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"article-title":"Superb benchmark","year":"2023","author":"wen Yang","key":"ref27"}],"event":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10192576\/10192577\/10193460.pdf?arnumber=10193460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T15:43:00Z","timestamp":1709307780000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10193460\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icasspw59220.2023.10193460","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}