{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T04:46:20Z","timestamp":1748493980863,"version":"3.28.0"},"reference-count":30,"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\/icassp43922.2022.9746097","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7107-7111","source":"Crossref","is-referenced-by-count":4,"title":["An Exploration of Hubert with Large Number of Cluster Units and Model Assessment Using Bayesian Information Criterion"],"prefix":"10.1109","author":[{"given":"Takashi","family":"Maekaku","sequence":"first","affiliation":[{"name":"Yahoo Japan Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuya","family":"Fujita","sequence":"additional","affiliation":[{"name":"Yahoo Japan Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Recent developments on ESPnet toolkit boosted by conformer","year":"2020","author":"guo","key":"ref30"},{"article-title":"SU-PERB: Speech processing universal performance benchmark","year":"2021","author":"yang","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688137"},{"key":"ref12","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language under-standing","author":"kenton","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176344136"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1755"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1182"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1465"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1503"},{"key":"ref18","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","author":"gutmann","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref19","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Adv in NeurIPS"},{"key":"ref28","first-page":"79","article-title":"MDL-based context-dependent subword modeling for speech recognition","volume":"21","author":"shinoda","year":"2000","journal-title":"Acoustical Science and Technology"},{"key":"ref4","article-title":"Unsupervised speech recognition","volume":"34","author":"baevski","year":"2021","journal-title":"Adv in NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758133"},{"key":"ref3","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107295360"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"oord","key":"ref5"},{"key":"ref8","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Adv in NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref2","article-title":"The zero resource speech benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","author":"nguyen","year":"2020","journal-title":"Workshop on Self-Supervised Learning for Speech and Audio Processing NeurIPS"},{"key":"ref9","article-title":"HuBERT: How much can a bad teacher benefit ASR pre-training","author":"hsu","year":"2020","journal-title":"Workshop on Self-Supervised Learning for Speech and Audio Processing NeurIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2743"},{"article-title":"RoBERTa: A robustly optimized bert pretraining approach","year":"2019","author":"liu","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-441"},{"article-title":"Reducing transformer depth on demand with structured dropout","year":"2019","author":"fan","key":"ref26"},{"key":"ref25","first-page":"377","article-title":"BLiMP: The benchmark of linguistic minimal pairs for english","volume":"8","author":"warstadt","year":"2020","journal-title":"Trans AC"}],"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\/09746097.pdf?arnumber=9746097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:08:31Z","timestamp":1660594111000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746097","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}