{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:52:36Z","timestamp":1772905956542,"version":"3.50.1"},"reference-count":68,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013290","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2018AAA0102504"],"award-info":[{"award-number":["2018AAA0102504"]}],"id":[{"id":"10.13039\/501100013290","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Shaanxi","award":["2021GY-025"],"award-info":[{"award-number":["2021GY-025"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3120644","type":"journal-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T22:52:54Z","timestamp":1634770374000},"page":"3242-3254","source":"Crossref","is-referenced-by-count":7,"title":["Synthesizing Spoken Descriptions of Images"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1826-7419","authenticated-orcid":false,"given":"Xinsheng","family":"Wang","sequence":"first","affiliation":[]},{"given":"Justin","family":"van der Hout","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3081-8781","authenticated-orcid":false,"given":"Jihua","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5631-2893","authenticated-orcid":false,"given":"Mark","family":"Hasegawa-Johnson","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0693-8852","authenticated-orcid":false,"given":"Odette","family":"Scharenborg","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3053391"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1759"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2973896"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2872106"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1006"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3067"},{"key":"ref37","first-page":"7603","article-title":"Align or attend? Toward more efficient and accurate spoken word discovery using speech-to-image retrieval","author":"wang","year":"2021","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2996082"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01205-0"},{"key":"ref34","first-page":"1","article-title":"Learning fine-grained semantics in spoken language using visual grounding","author":"wang","year":"2021","journal-title":"Proc IEEE Int Symp Circuits Syst"},{"key":"ref60","article-title":"The LJ speech dataset","author":"ito","year":"2017"},{"key":"ref62","article-title":"Image captioning using deep stacked LSTMs, contextual word embeddings and data augmentation","author":"katiyar","year":"2021"},{"key":"ref61","first-page":"10 327","article-title":"Normalized and geometry-aware self-attention network for image captioning","author":"guo","year":"2020","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref63","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_40"},{"key":"ref64","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020"},{"key":"ref27","first-page":"11137","article-title":"Image captioning: Transforming objects into words","author":"herdade","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref29","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref67","first-page":"146","article-title":"Investigating RNN-based speech enhancement methods for noise-robust text-to-speech","author":"valentini-botinhao","year":"2016","journal-title":"Semantic Search over the Web"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_5"},{"key":"ref1","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018320"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.080"},{"key":"ref26","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref59","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref56","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref55","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016"},{"key":"ref54","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref10","article-title":"Ethnologue: Languages of the world, 18th ed","author":"lewis","year":"2015"},{"key":"ref11","article-title":"Image2speech: Automatically generating audio descriptions of images","author":"hasegawa-johnson","year":"2017","journal-title":"Proc Int Conf Natural Lang Signal Speech Process"},{"key":"ref40","first-page":"185","article-title":"XNMT: The extensible neural machine translation toolkit","author":"neubig","year":"2018","journal-title":"Proc 13th Conf Assoc Mach Transl Amer"},{"key":"ref12","article-title":"Text-free image-to-speech synthesis using learned segmental units","author":"hsu","year":"2020"},{"key":"ref13","article-title":"Learning hierarchical discrete linguistic units from visually-grounded speech","author":"harwath","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3071541"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2870"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2097"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2050411"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref8","first-page":"2469","article-title":"Deep reinforcement learning for sequence-to-sequence models","volume":"31","author":"keneshloo","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.64"},{"key":"ref49","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref45","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc Text Summarization Branches Out"},{"key":"ref48","first-page":"73","article-title":"The 2014 KIT IWSLT speech-to-text systems for English, German and Italian","author":"kilgour","year":"2014","journal-title":"Proc Int Workshop Spoken Lang Transl"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref41","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref43","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09581052.pdf?arnumber=9581052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:54Z","timestamp":1652194434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9581052\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3120644","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}