{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:53:44Z","timestamp":1772906024167,"version":"3.50.1"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["JP17H06101"],"award-info":[{"award-number":["JP17H06101"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google AI Focused Research Awards Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3071541","type":"journal-article","created":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T20:03:03Z","timestamp":1617825783000},"page":"55144-55154","source":"Crossref","is-referenced-by-count":12,"title":["End-to-End Image-to-Speech Generation for Untranscribed Unknown Languages"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5755-415X","authenticated-orcid":false,"given":"Johanes","family":"Effendi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5509-8963","authenticated-orcid":false,"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-3803","authenticated-orcid":false,"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","author":"ito","year":"2017","journal-title":"The LJ speech dataset"},{"key":"ref38","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","volume":"29","author":"harwath","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref36","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref35","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"lavie","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3115\/1557690.1557736"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2922617"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947338"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495637"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"key":"ref15","first-page":"3204","article-title":"Unsupervised word discovery from speech using automatic segmentation into syllable-like units","author":"r\u00e4s\u00e4nen","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003853"},{"key":"ref17","first-page":"1","article-title":"Image2speech: Automatically generating audio descriptions of images","author":"hasegawa-johnson","year":"2017","journal-title":"Proc ICNLSSP"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2870"},{"key":"ref19","article-title":"Text-free image-to-speech synthesis using learned segmental units","author":"hsu","year":"2020","journal-title":"Proc NeurIPS Workshop Self-supervised Learn Speech Audio Process"},{"key":"ref28","first-page":"139","article-title":"Collecting image annotations using Amazon’s mechanical Turk","author":"rashtchian","year":"2010","journal-title":"Proc NAACL HLT Workshop Creating Speech Lang Data Amazon’s Mech Turk"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2743"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.032"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.033"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3232"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461761"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268953"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3033"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00769"},{"key":"ref22","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/aic.690370209"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","first-page":"6306","article-title":"Neural discrete representation learning","volume":"30","author":"van den oord","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref25","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09398708.pdf?arnumber=9398708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:57:32Z","timestamp":1639771052000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9398708\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3071541","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}