{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T05:48:25Z","timestamp":1745300905109},"reference-count":33,"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\/icassp49357.2023.10096788","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Do Coarser Units Benefit Cluster Prediction-Based Speech Pre-Training?"],"prefix":"10.1109","author":[{"given":"Ali","family":"Elkahky","sequence":"first","affiliation":[{"name":"Meta Inc."}]},{"given":"Wei-Ning","family":"Hsu","sequence":"additional","affiliation":[{"name":"Meta Inc."}]},{"given":"Paden","family":"Tomasello","sequence":"additional","affiliation":[{"name":"Meta Inc."}]},{"given":"Tu-Anh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Meta Inc."}]},{"given":"Robin","family":"Algayres","sequence":"additional","affiliation":[{"name":"Meta Inc."}]},{"given":"Yossi","family":"Adi","sequence":"additional","affiliation":[{"name":"Meta Inc."}]},{"given":"Jade","family":"Copet","sequence":"additional","affiliation":[{"name":"Meta Inc."}]},{"given":"Emmanuel","family":"Dupoux","sequence":"additional","affiliation":[{"name":"Meta Inc."}]},{"given":"Abdelrahman","family":"Mohamed","sequence":"additional","affiliation":[{"name":"Meta Inc."}]}],"member":"263","reference":[{"article-title":"Are word boundaries useful for unsupervised language learning?","year":"2022","author":"nguyen","key":"ref13"},{"article-title":"Pre-training transformer decoder for end-to-end asr model with un-paired speech data","year":"2022","author":"ao","key":"ref12"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-538"},{"key":"ref14","article-title":"V-measure: A conditional entropy-based external cluster evaluation measure","author":"rosenberg","year":"2007","journal-title":"EMNLP-CoNLL"},{"key":"ref31","article-title":"Class-based n-gram models of natural language","author":"brown","year":"1992","journal-title":"Computational Linguistics"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"article-title":"Word segmentation on discovered phone units with dynamic programming and self-supervised scoring","year":"2022","author":"kamper","key":"ref11"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10652"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref2","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref1","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"NeurIPS"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"liu","key":"ref17"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref16"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref18","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"article-title":"Self-supervised learning with random-projection quantizer for speech recognition","year":"2022","author":"chiu","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-981"},{"key":"ref20","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"International Conference on Ma-chine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"van den oord","key":"ref21"},{"key":"ref28","article-title":"Librispeech: an asr corpus based on public do-main audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"article-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","year":"2019","author":"lewis","key":"ref27"},{"article-title":"Distilhubert: Speech representation learning by layer-wise distillation of hidden-unit bert","year":"2021","author":"chang","key":"ref29"},{"article-title":"Generative spoken dialogue language modeling","year":"2022","author":"nguyen","key":"ref8"},{"key":"ref7","article-title":"On generative spoken language modeling from raw audio","author":"lakhotia","year":"2021","journal-title":"TACL"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"year":"2022","author":"wu","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10096788.pdf?arnumber=10096788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:04:36Z","timestamp":1700489076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096788\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096788","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}