{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:06:46Z","timestamp":1740100006988,"version":"3.37.3"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414899","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"3710-3714","source":"Crossref","is-referenced-by-count":4,"title":["A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery"],"prefix":"10.1109","author":[{"given":"Bolaji","family":"Yusuf","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lucas","family":"Ondel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lukas","family":"Burget","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Cernocky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murat","family":"Saraclar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2148"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2224"},{"key":"ref13","article-title":"Dirichlet processes","author":"teh","year":"2010","journal-title":"Encyclopedia of Machine Learning"},{"key":"ref14","article-title":"Discovering Acoustic Units from Speech: A Bayesian Approach","author":"ondel","year":"2021","journal-title":"Ph D thesis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461545"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953258"},{"key":"ref17","article-title":"Auto-encoding Variational Bayes","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2010.06.003"},{"article-title":"A very low resource language speech corpus for computational language documentation experiments","year":"2017","author":"godard","key":"ref19"},{"key":"ref28","article-title":"Adam: A method for stochastic gradient descent","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1214\/06-BA104"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268953"},{"key":"ref6","article-title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","author":"baevski","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref29","article-title":"Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech","author":"harwath","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref8","first-page":"40","article-title":"A nonparametric Bayesian approach to acoustic model discovery","author":"lee","year":"2012","journal-title":"Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics Long Papers-Volume 1"},{"key":"ref7","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"The Zero Resource Speech Challenge 2015","author":"versteegh","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.033"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2017.11.008"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1096"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639248"},{"article-title":"The DARPA TIMIT acoustic-phonetic continuous speech corpus CDROM. NTIS order number PB91-505065","year":"1990","author":"garofolo","key":"ref21"},{"key":"ref24","article-title":"Developments of Swahili resources for an automatic speech recognition system","author":"gelas","year":"2012","journal-title":"SLTU - Workshop on Spoken Language Technologies for Under-Resourced Languages"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2005-467","article-title":"An Amharic Speech Corpus for Large Vocabulary Continuous Speech Recognition","author":"abate","year":"2005","journal-title":"INTERSPEECH-2005"},{"key":"ref26","article-title":"Speech technologies for african languages: Example of a multilingual calculator for education","author":"besacier","year":"2015","journal-title":"InterSpeech"},{"key":"ref25","article-title":"Collecting Resources in Sub-Saharan African Languages for Automatic Speech Recognition: a Case Study of Wolof","author":"gauthier","year":"2016","journal-title":"LREC"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414899.pdf?arnumber=9414899","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:24:49Z","timestamp":1672129489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414899\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414899","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}