{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:45:47Z","timestamp":1730231147860,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446474","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12336-12340","source":"Crossref","is-referenced-by-count":0,"title":["Learning Contextualized Representation on Discrete Space Via Hierarchical Product Quantization"],"prefix":"10.1109","author":[{"given":"Hyung Yong","family":"Kim","sequence":"first","affiliation":[{"name":"42dot Inc,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byeong-Yeol","family":"Kim","sequence":"additional","affiliation":[{"name":"42dot Inc,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunkyu","family":"Lim","sequence":"additional","affiliation":[{"name":"42dot Inc,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jihwan","family":"Park","sequence":"additional","affiliation":[{"name":"42dot Inc,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinseok","family":"Park","sequence":"additional","affiliation":[{"name":"42dot Inc,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youshin","family":"Lim","sequence":"additional","affiliation":[{"name":"42dot Inc,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seung Woo","family":"Yu","sequence":"additional","affiliation":[{"name":"42dot Inc,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanbin","family":"Lee","sequence":"additional","affiliation":[{"name":"42dot Inc,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"article-title":"Image bert pre-training with online tokenizer","volume-title":"Proc. ICLR","author":"Zhou","key":"ref3"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. ICML","author":"Srinivas","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume-title":"Proc. NeurIPS","author":"Choi","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10558"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"article-title":"Textually pretrained speech language models","year":"2023","author":"Hassid","key":"ref12"},{"article-title":"Unsupervised speech recognition","volume-title":"Proc. NeurIPS","author":"Baevski","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023187"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095373"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094726"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"article-title":"Beats: Audio pre-training with acoustic tokenizers","volume-title":"Proc. ICML","author":"Chen","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683535"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446474.pdf?arnumber=10446474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:19:04Z","timestamp":1722575944000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446474\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446474","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}