{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:23:48Z","timestamp":1775229828831,"version":"3.50.1"},"reference-count":27,"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\/icassp48485.2024.10448331","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12526-12530","source":"Crossref","is-referenced-by-count":2,"title":["Do Learned Speech Symbols Follow Zipf\u2019s Law?"],"prefix":"10.1109","author":[{"given":"Shinnosuke","family":"Takamichi","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroki","family":"Maeda","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joonyong","family":"Park","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daisuke","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Zipf","year":"1949","journal-title":"Human Behaviour and the Principle of Least Effort"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-014-0585-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59377-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1515\/cogl.2009.022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-022-02142-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1321"},{"key":"ref7","first-page":"2146","article-title":"Emergence of language with multi-agent games: Learning to communicate with sequences of symbols","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Havrylov"},{"key":"ref8","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the ACL"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-981"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3288409"},{"key":"ref11","author":"van den Oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref12","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NIPS","volume":"33","author":"Baevski"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/ssw.2021-37"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-444"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref19","article-title":"Analysis of degraded noisy voice and application to other languages using generative spoken language model","volume-title":"Annual meeting of acoustic society of Japan","author":"Park"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-926"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.13536"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2020.124309"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref24","article-title":"Multiagent cooperation and the emergence of (natural) language","author":"Lazaridou","year":"2017","journal-title":"ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1384"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.4324\/9781315009421"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-srw.6"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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\/10448331.pdf?arnumber=10448331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:52:26Z","timestamp":1722660746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448331\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448331","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}