{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T11:16:05Z","timestamp":1730286965794,"version":"3.28.0"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T00:00:00Z","timestamp":1637193600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T00:00:00Z","timestamp":1637193600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T00:00:00Z","timestamp":1637193600000},"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":[[2021,11,18]]},"DOI":"10.1109\/o-cocosda202152914.2021.9660413","type":"proceedings-article","created":{"date-parts":[[2022,1,3]],"date-time":"2022-01-03T20:19:17Z","timestamp":1641241157000},"page":"37-42","source":"Crossref","is-referenced-by-count":1,"title":["Self-Supervised Spoken Question Understanding and Speaking with Automatic Vocabulary Learning"],"prefix":"10.1109","author":[{"given":"Keisuke","family":"Toyoda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Kimura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingxin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kent","family":"Hino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kosuke","family":"Mori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahiro","family":"Shinozaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.790"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053326"},{"key":"ref12","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume":"1","author":"macqueen","year":"1967","journal-title":"BSMPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2164"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2027"},{"key":"ref3","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Learning hierarchical discrete linguistic units from visually-grounded speech","author":"harwath","year":"2019","journal-title":"CoRR vol abs\/1911 09602"},{"key":"ref5","first-page":"9758","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume":"33","author":"alwassel","year":"2020","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/810"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1016\/0167-2789(90)90087-6","article-title":"The symbol grounding problem","volume":"42","author":"harnad","year":"1990","journal-title":"Physica D Nonlinear Phenomena"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269008"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1007\/BF00849726","article-title":"Grounding language in perception","volume":"8","author":"siskind","year":"1994","journal-title":"Artificial Intelligence Review"}],"event":{"name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","start":{"date-parts":[[2021,11,18]]},"location":"Singapore, Singapore","end":{"date-parts":[[2021,11,20]]}},"container-title":["2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9660212\/9660400\/09660413.pdf?arnumber=9660413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:56:37Z","timestamp":1652201797000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9660413\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,18]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda202152914.2021.9660413","relation":{},"subject":[],"published":{"date-parts":[[2021,11,18]]}}}