{"id":"https://openalex.org/W3206387123","doi":"https://doi.org/10.1109/taslp.2021.3120644","title":"Synthesizing Spoken Descriptions of Images","display_name":"Synthesizing Spoken Descriptions of Images","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3206387123","doi":"https://doi.org/10.1109/taslp.2021.3120644","mag":"3206387123"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3120644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3120644","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021472684","display_name":"Xinsheng Wang","orcid":"https://orcid.org/0000-0003-1826-7419"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["CN","NL"],"is_corresponding":true,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China, 710049 (e-mail: wangxinsheng@stu.xjtu.edu.cn)","Multimedia Computing Group, Delft University of Technology, 2628 CD Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China, 710049 (e-mail: wangxinsheng@stu.xjtu.edu.cn)","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, 2628 CD Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024937302","display_name":"Justin van der Hout","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Justin van der Hout","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delf, Netherlands, (e-mail: justinvdh@gmail.com)","Multimedia Computing Group, Delft University of Technology, 2628 CD Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delf, Netherlands, (e-mail: justinvdh@gmail.com)","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, 2628 CD Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068185614","display_name":"Jihua Zhu","orcid":"https://orcid.org/0000-0002-3081-8781"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihua Zhu","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, 12480 Xi'an, Shannxi, China, 710049 (e-mail: zhujh@xjtu.edu.cn)","School of Software Engineering, Xi'an Jiaotong University, Xi'an 710049, China","School of Software Engineering, Xi'an Jiaotong University, Xi'an 710049, China,"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, 12480 Xi'an, Shannxi, China, 710049 (e-mail: zhujh@xjtu.edu.cn)","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an 710049, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an 710049, China,","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, Illinois, United States, 61801 (e-mail: jhasegaw@illinois.edu)","Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, Illinois, United States, 61801 (e-mail: jhasegaw@illinois.edu)","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":["Multimedia Computing Group, Technische Universiteit Delft Faculteit Elektrotechniek Wiskunde en Informatica, 225112 Delft, Netherlands, 2628 XE (e-mail: o.e.scharenborg@tudelft.nl)","Multimedia Computing Group, Delft University of Technology, 2628 CD Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Technische Universiteit Delft Faculteit Elektrotechniek Wiskunde en Informatica, 225112 Delft, Netherlands, 2628 XE (e-mail: o.e.scharenborg@tudelft.nl)","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, 2628 CD Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021472684"],"corresponding_institution_ids":["https://openalex.org/I87445476","https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.6782,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71874494,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"3242","last_page":"3254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9411470890045166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.812811017036438},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7002264261245728},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6920073628425598},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6448696255683899},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5550928115844727},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49762824177742004},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49133744835853577},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44815337657928467}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9411470890045166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.812811017036438},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7002264261245728},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6920073628425598},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6448696255683899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5550928115844727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49762824177742004},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49133744835853577},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44815337657928467},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3120644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3120644","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:tudelft.nl:uuid:914070cb-d4fe-4bad-8064-bc83154b895b","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:914070cb-d4fe-4bad-8064-bc83154b895b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2300736770","display_name":null,"funder_award_id":"(CSC)","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G3586343731","display_name":null,"funder_award_id":"2021GY-025","funder_id":"https://openalex.org/F4320336350","funder_display_name":"Key Research and Development Projects of Shaanxi Province"},{"id":"https://openalex.org/G6740317072","display_name":null,"funder_award_id":"2018AAA0102504","funder_id":"https://openalex.org/F4320336026","funder_display_name":"National Key Research and Development Program of China Stem Cell and Translational Research"},{"id":"https://openalex.org/G8589651859","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320336026","display_name":"National Key Research and Development Program of China Stem Cell and Translational Research","ror":null},{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":99,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1514535095","https://openalex.org/W1524333225","https://openalex.org/W1686810756","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W1987835821","https://openalex.org/W2062955551","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2123301721","https://openalex.org/W2131179926","https://openalex.org/W2154652894","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2519091744","https://openalex.org/W2556930864","https://openalex.org/W2575842049","https://openalex.org/W2603567530","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2796315435","https://openalex.org/W2803259101","https://openalex.org/W2888867175","https://openalex.org/W2895420168","https://openalex.org/W2907262790","https://openalex.org/W2946200149","https://openalex.org/W2949382160","https://openalex.org/W2950133079","https://openalex.org/W2962862718","https://openalex.org/W2963084599","https://openalex.org/W2963260927","https://openalex.org/W2963403868","https://openalex.org/W2963902314","https://openalex.org/W2963992143","https://openalex.org/W2964243274","https://openalex.org/W2965846473","https://openalex.org/W2968831808","https://openalex.org/W2970730223","https://openalex.org/W2971310675","https://openalex.org/W2971709506","https://openalex.org/W2986670728","https://openalex.org/W2988907666","https://openalex.org/W2990818246","https://openalex.org/W2995680346","https://openalex.org/W2997591391","https://openalex.org/W3005578234","https://openalex.org/W3027851323","https://openalex.org/W3033411150","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3095030004","https://openalex.org/W3096249149","https://openalex.org/W3097538987","https://openalex.org/W3102219307","https://openalex.org/W3114436296","https://openalex.org/W3123798147","https://openalex.org/W3130016944","https://openalex.org/W3132706255","https://openalex.org/W3155217823","https://openalex.org/W3158565912","https://openalex.org/W3161204797","https://openalex.org/W3174311593","https://openalex.org/W3204007566","https://openalex.org/W4206865574","https://openalex.org/W4287324741","https://openalex.org/W4288329833","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6630875275","https://openalex.org/W6631362777","https://openalex.org/W6637373629","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6729977899","https://openalex.org/W6739901393","https://openalex.org/W6749352598","https://openalex.org/W6751792830","https://openalex.org/W6763643401","https://openalex.org/W6763832098","https://openalex.org/W6770596778","https://openalex.org/W6775036401","https://openalex.org/W6778823374","https://openalex.org/W6787100281","https://openalex.org/W6791006397","https://openalex.org/W6794343169","https://openalex.org/W6795412237","https://openalex.org/W6802821423","https://openalex.org/W6898505805","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Image":[0],"captioning":[1,13],"technology":[2],"has":[3],"great":[4],"potential":[5],"in":[6,71],"many":[7],"scenarios.":[8],"However,":[9],"current":[10],"text-based":[11],"image":[12],"methods":[14,78],"cannot":[15],"be":[16,156],"applied":[17],"to":[18,26,90,104,158],"approximately":[19],"half":[20],"of":[21,30,48,58,108,128],"the":[22,39,68,82,92,122,141],"world's":[23],"languages":[24,28],"due":[25],"these":[27],"lack":[29],"a":[31,64],"written":[32],"form.":[33],"To":[34],"solve":[35],"this":[36],"problem,":[37],"recently":[38],"image-to-speech":[40,69,99,165],"task":[41,70],"was":[42],"proposed,":[43],"which":[44],"generates":[45],"spoken":[46,106],"descriptions":[47,107],"images":[49,109],"bypassing":[50,110,166],"any":[51],"text":[52,112,167],"via":[53],"an":[54,97],"intermediate":[55],"representation":[56],"consisting":[57],"phonemes":[59,114,169],"(image-to-phoneme).":[60],"Here,":[61],"we":[62],"present":[63],"comprehensive":[65],"study":[66],"on":[67,121,140],"which,":[72],"1)":[73,133],"several":[74,146],"representative":[75],"image-to-text":[76,135],"generation":[77],"are":[79,88,119],"implemented":[80],"for":[81],"image-to-phoneme":[83,93,142,160],"task,":[84,94,143],"2)":[85,145],"objective":[86],"metrics":[87],"sought":[89],"evaluate":[91,159],"and":[95,113,144,153,168],"3)":[96,163],"end-to-end":[98,164],"model":[100],"that":[101,132],"is":[102,115,170],"able":[103],"synthesize":[105],"both":[111],"proposed.":[116],"Extensive":[117],"experiments":[118,130],"conducted":[120],"public":[123],"benchmark":[124],"database":[125],"Flickr8k.":[126],"Results":[127],"our":[129],"demonstrate":[131],"State-of-the-art":[134],"models":[136],"can":[137,155],"perform":[138],"well":[139],"evaluation":[147],"metrics,":[148],"including":[149],"BLEU3,":[150],"BLEU4,":[151],"BLEU5,":[152],"ROUGE-L":[154],"used":[157],"performance.":[161],"Finally,":[162],"feasible.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}