{"id":"https://openalex.org/W3161053832","doi":"https://doi.org/10.1109/icassp39728.2021.9414021","title":"Show and Speak: Directly Synthesize Spoken Description of Images","display_name":"Show and Speak: Directly Synthesize Spoken Description of Images","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161053832","doi":"https://doi.org/10.1109/icassp39728.2021.9414021","mag":"3161053832"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://resolver.tudelft.nl/uuid:5ce6b416-ef81-41b6-adf9-8456cf455992","any_repository_has_fulltext":true},"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":false,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, China","School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053373302","display_name":"Siyuan Feng","orcid":"https://orcid.org/0000-0003-2531-8480"},"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":"Siyuan Feng","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, 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\u2019an Jiaotong University, Xi\u2019an, China","School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, 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":["University of Illinois at Urbana-Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2823,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.53142819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4190","last_page":"4194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9987000226974487,"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9312239289283752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8328955173492432},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7081193327903748},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6301734447479248},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.585791826248169},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5469720959663391},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5287767648696899},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5200502276420593},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5098387598991394},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4344120919704437}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9312239289283752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8328955173492432},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7081193327903748},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6301734447479248},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.585791826248169},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5469720959663391},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5287767648696899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5200502276420593},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5098387598991394},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4344120919704437},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:5ce6b416-ef81-41b6-adf9-8456cf455992","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:5ce6b416-ef81-41b6-adf9-8456cf455992","pdf_url":"http://resolver.tudelft.nl/uuid:5ce6b416-ef81-41b6-adf9-8456cf455992","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":"conference paper"}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:5ce6b416-ef81-41b6-adf9-8456cf455992","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:5ce6b416-ef81-41b6-adf9-8456cf455992","pdf_url":"http://resolver.tudelft.nl/uuid:5ce6b416-ef81-41b6-adf9-8456cf455992","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":"conference paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3161053832.pdf"},"referenced_works_count":38,"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/W1895577753","https://openalex.org/W2108598243","https://openalex.org/W2220981600","https://openalex.org/W2277195237","https://openalex.org/W2519091744","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2888867175","https://openalex.org/W2895420168","https://openalex.org/W2896348597","https://openalex.org/W2949382160","https://openalex.org/W2962862718","https://openalex.org/W2963084599","https://openalex.org/W2963992143","https://openalex.org/W2964243274","https://openalex.org/W2968831808","https://openalex.org/W2986670728","https://openalex.org/W2988907666","https://openalex.org/W2990818246","https://openalex.org/W2997591391","https://openalex.org/W3034655362","https://openalex.org/W3095030004","https://openalex.org/W3096249149","https://openalex.org/W3123798147","https://openalex.org/W4206865574","https://openalex.org/W6620707391","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6630875275","https://openalex.org/W6631362777","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2998781440"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"new":[4],"model,":[5],"referred":[6],"to":[7,22,89],"as":[8,50],"the":[9,17,30,54,69,77,84],"show":[10],"and":[11,52,106],"speak":[12],"(SAS)":[13],"model":[14],"that,":[15],"for":[16,32,94,101],"first":[18],"time,":[19],"is":[20,42,66,87,108],"able":[21,88],"directly":[23],"synthesize":[24,90],"spoken":[25,92,99],"descriptions":[26,93,100],"of":[27,40,56],"images,":[28,95],"bypassing":[29,104],"need":[31],"any":[33],"text":[34,105],"or":[35],"phonemes.":[36],"The":[37,62],"basic":[38],"structure":[39],"SAS":[41,86],"an":[43,48],"encoder-decoder":[44],"architecture":[45],"that":[46,58,83,97],"takes":[47],"image":[49],"input":[51],"predicts":[53],"spectrogram":[55,71],"speech":[57,64],"describes":[59],"this":[60],"image.":[61],"final":[63],"audio":[65],"obtained":[67],"from":[68],"predicted":[70],"via":[72],"WaveNet.":[73],"Extensive":[74],"experiments":[75],"on":[76],"public":[78],"benchmark":[79],"database":[80],"Flickr8k":[81],"demonstrate":[82],"proposed":[85],"natural":[91],"indicating":[96],"synthesizing":[98],"images":[102],"while":[103],"phonemes":[107],"feasible.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
