{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:36:47Z","timestamp":1730230607058,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747259","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"3268-3272","source":"Crossref","is-referenced-by-count":2,"title":["Self Supervised Representation Learning with Deep Clustering for Acoustic Unit Discovery from Raw Speech"],"prefix":"10.1109","author":[{"given":"Varun","family":"Krishna","sequence":"first","affiliation":[{"name":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sriram","family":"Ganapathy","sequence":"additional","affiliation":[{"name":"Indian Institute of Science,Learning and Extraction of Acoustic Patterns (LEAP) Lab,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2020"},{"key":"ref32","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref31","article-title":"Libri-light: A bench-mark for ASR with limited or no supervision","author":"kahn","year":"2019","journal-title":"CoRR"},{"key":"ref30","first-page":"5206","article-title":"Librispeech: An ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"key":"ref34","article-title":"Blimp: A benchmark of linguistic minimal pairs for english","author":"warstadt","year":"2019","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269011"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269013"},{"year":"0","key":"ref14","article-title":"learning problem-agnostic speech representations from multiple self-supervised tasks"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1503"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"article-title":"Deep Clustering for Unsupervised Learning of Visual Features","year":"2019","author":"caron","key":"ref28"},{"key":"ref4","first-page":"501","article-title":"A segment model based approach to speech recognition","author":"lee","year":"1988","journal-title":"ICASSP"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref27"},{"year":"0","key":"ref3","article-title":"an investigation on the use of acoustic sub-word units for automatic speech recognition"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-638"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/1557690.1557736"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2743"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268953"},{"year":"0","key":"ref2","article-title":"unsupervised pattern discovery in speech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1755"},{"article-title":"Generative spoken language modeling from raw audio","year":"2021","author":"lakhotia","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3033"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","year":"2020","author":"baevski","key":"ref24"},{"article-title":"vqwav2vec: Self-Supervised Learning of Discrete Speech Representations","year":"2020","author":"baevski","key":"ref23"},{"article-title":"Neural Discrete Representation Learning","year":"2018","author":"van den oord","key":"ref26"},{"article-title":"Representation Learning with Contrastive Predictive Coding","year":"2019","author":"van den oord","key":"ref25"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747259.pdf?arnumber=9747259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:09:08Z","timestamp":1660579748000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747259\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747259","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}