{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T17:46:54Z","timestamp":1779299214104,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100009518","name":"Tokyo University of Agriculture and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009518","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,29]]},"DOI":"10.1109\/ro-man53752.2022.9900685","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:57:30Z","timestamp":1664567850000},"page":"244-251","source":"Crossref","is-referenced-by-count":3,"title":["Talk to Kotaro: a web crowdsourcing study on the impact of phone and prosody choice for synthesized speech on human impression"],"prefix":"10.1109","author":[{"given":"Antonio Galiza Cerdeira","family":"Gonzalez","sequence":"first","affiliation":[{"name":"University of Agriculture and Technology,School of Engineering,Mechanical Systems Department of Tokyo,Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"WingSum","family":"Lo","sequence":"additional","affiliation":[{"name":"University of Agriculture and Technology,School of Engineering,Mechanical Systems Department of Tokyo,Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ikuo","family":"Mizuuchi","sequence":"additional","affiliation":[{"name":"University of Agriculture and Technology,School of Engineering,Mechanical Systems Department of Tokyo,Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3371382.3378330"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-192"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1811"},{"key":"ref32","article-title":"Sound analogies with phoneme embeddings","author":"silfverberg","year":"2018","journal-title":"Proceedings of the Society for Computation in Linguistics (SCiL) 2018"},{"key":"ref31","article-title":"Waitress 2.10 documentation","year":"0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24571-8_17"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2418092"},{"key":"ref36","article-title":"Facial Emotion Recognition (FER) using Keras","author":"sharma","year":"2020","journal-title":"Analytics Vidhya"},{"key":"ref35","article-title":"my-voice-analysis","year":"2019","journal-title":"my-voice-analysis"},{"key":"ref34","first-page":"3490","article-title":"Joint Grapheme and Phoneme Embeddings for Contextual End-to-End ASR","author":"chen","year":"2019","journal-title":"InterSpeech"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.549360"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2014.05.009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-018-0266-9"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1007\/s12599-014-0334-4","article-title":"Industry 4.0","volume":"6","author":"lasi","year":"2014","journal-title":"Business & Information Systems Engineering"},{"key":"ref13","first-page":"1","article-title":"What is society 5.0","volume":"5","author":"deguchi","year":"2020","journal-title":"Society"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3371382.3380739"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5565\/rev\/elcvia.795"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24837-8_10"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106172"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3421486"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN46459.2019.8956240"},{"key":"ref28","first-page":"1","article-title":"Phoneme frequencies follow a Yule distribution","volume":"4","author":"tambovtsev","year":"2007","journal-title":"SKASE Journal of Theoretical Linguistics"},{"key":"ref4","year":"1999","journal-title":"Handbook of the International Phonetic Association A Guide to the Use of the International Phonetic Alphabet"},{"key":"ref27","article-title":"IPA charts and sub-charts in four fonts","year":"0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2015.1093856"},{"key":"ref6","first-page":"3","article-title":"Synaesthesia– a window into perception, thought and language","volume":"8","author":"ramachandran","year":"2001","journal-title":"Journal of Consciousness Studies"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2020.570895"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2015.7364114"},{"key":"ref8","article-title":"A JavaScript Framework for Crowdsourced Human-Robot Interaction Experiments: RemoteHRI","author":"lau","year":"2020","journal-title":"Association for the Advancement of Artificial Intelligence"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-010-0070-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1641165"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2011.6005284"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3405450"},{"key":"ref20","article-title":"eSpeak text to speech","author":"duddington","year":"2012"},{"key":"ref22","article-title":"jQuery in Action","author":"bibeault","year":"2015","journal-title":"Simon & Schuster"},{"key":"ref21","article-title":"Comparative study on Python web frameworks: Flask and Django","author":"ghimire","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5057\/isase.2019-C000037"},{"key":"ref24","first-page":"882","article-title":"Sqlite: Light database system","volume":"44","author":"bhosale","year":"2015","journal-title":"Int J Comput Sci Mob Comput"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3434073.3444665"},{"key":"ref23","article-title":"Recorderjs","author":"diamond","year":"2016"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-19"},{"key":"ref26","article-title":"Docker in action","author":"nickoloff","year":"2019","journal-title":"Simon & Schuster"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.084"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICITISEE.2018.8720983"}],"event":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","location":"Napoli, Italy","start":{"date-parts":[[2022,8,29]]},"end":{"date-parts":[[2022,9,2]]}},"container-title":["2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9900506\/9900507\/09900685.pdf?arnumber=9900685","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:04:59Z","timestamp":1667516699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9900685\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/ro-man53752.2022.9900685","relation":{},"subject":[],"published":{"date-parts":[[2022,8,29]]}}}