{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:00:50Z","timestamp":1776884450933,"version":"3.51.2"},"reference-count":32,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096099","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":15,"title":["Analyzing Acoustic Word Embeddings from Pre-Trained Self-Supervised Speech Models"],"prefix":"10.1109","author":[{"given":"Ramon","family":"Sanabria","sequence":"first","affiliation":[{"name":"The University of Edinburgh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[{"name":"The University of Edinburgh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sharon","family":"Goldwater","sequence":"additional","affiliation":[{"name":"The University of Edinburgh"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.04.008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383625"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269008"},{"key":"ref31","article-title":"Towards end-to-end unsupervised speech recognition","author":"liu","year":"2022","journal-title":"arXiv preprint arXiv 2204 02492"},{"key":"ref30","article-title":"Unsupervised speech recognition","author":"baevski","year":"2021","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683639"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2364"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCS.2011.6140822"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"ref17","article-title":"Speech sequence embeddings using nearest neighbors contrastive learning","author":"robin","year":"2022","journal-title":"ICASSP"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383594"},{"key":"ref19","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref24","article-title":"Unsupervised neural and bayesian models for zero-resource speech processing","author":"kamper","year":"2017","journal-title":"thesis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.09.001"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.07.001"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref20","article-title":"A correspondence variational autoencoder for unsupervised acoustic word embeddings","author":"peng","year":"2020","journal-title":"NeurIPS workshop"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-304"},{"key":"ref28","article-title":"Montreal Forced Aligner","year":"0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268953"},{"key":"ref29","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv preprint arXiv 1807 03748"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846310"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2828"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1592"},{"key":"ref4","article-title":"Word-level acoustic modeling with convolutional vector regression","author":"maas","year":"2012","journal-title":"ICML Workshop"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.894524"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472619"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707765"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096099.pdf?arnumber=10096099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:59:52Z","timestamp":1700506792000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096099\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096099","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}