{"id":"https://openalex.org/W4396510248","doi":"https://doi.org/10.3390/electronics13091726","title":"Recent Advances in Synthesis and Interaction of Speech, Text, and Vision","display_name":"Recent Advances in Synthesis and Interaction of Speech, Text, and Vision","publication_year":2024,"publication_date":"2024-04-30","ids":{"openalex":"https://openalex.org/W4396510248","doi":"https://doi.org/10.3390/electronics13091726"},"language":"en","primary_location":{"id":"doi:10.3390/electronics13091726","doi":"https://doi.org/10.3390/electronics13091726","is_oa":true,"landing_page_url":"https://doi.org/10.3390/electronics13091726","pdf_url":"https://www.mdpi.com/2079-9292/13/9/1726/pdf?version=1714464728","source":{"id":"https://openalex.org/S4210202905","display_name":"Electronics","issn_l":"2079-9292","issn":["2079-9292"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2079-9292/13/9/1726/pdf?version=1714464728","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041138233","display_name":"Laura Orynbay","orcid":"https://orcid.org/0009-0006-4787-7944","observed_orcids":["https://orcid.org/0009-0006-4787-7944"]},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Laura Orynbay","raw_affiliation_strings":["Department of Artificial Intelligence Technologies, L.N. Gumilyov Eurasian National University, Astana 010008, Kazakhstan"],"raw_orcid":"https://orcid.org/0009-0006-4787-7944","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence Technologies, L.N. Gumilyov Eurasian National University, Astana 010008, Kazakhstan","institution_ids":["https://openalex.org/I10232997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080933533","display_name":"Razakhova Bibigul Shamshanovna","orcid":"https://orcid.org/0000-0002-8152-8661","observed_orcids":["https://orcid.org/0000-0002-8152-8661"]},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Bibigul Razakhova","raw_affiliation_strings":["Department of Artificial Intelligence Technologies, L.N. Gumilyov Eurasian National University, Astana 010008, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-8152-8661","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence Technologies, L.N. Gumilyov Eurasian National University, Astana 010008, Kazakhstan","institution_ids":["https://openalex.org/I10232997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027730478","display_name":"Peter Peer","orcid":"https://orcid.org/0000-0001-9744-4035","observed_orcids":["https://orcid.org/0000-0001-9744-4035"]},"institutions":[{"id":"https://openalex.org/I153976015","display_name":"University of Ljubljana","ror":"https://ror.org/05njb9z20","country_code":"SI","type":"education","lineage":["https://openalex.org/I153976015"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Peter Peer","raw_affiliation_strings":["Faculty of Computer and Information Science, University of Ljubljana, SI-1000 Ljubljana, Slovenia"],"raw_orcid":"https://orcid.org/0000-0001-9744-4035","affiliations":[{"raw_affiliation_string":"Faculty of Computer and Information Science, University of Ljubljana, SI-1000 Ljubljana, Slovenia","institution_ids":["https://openalex.org/I153976015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005642535","display_name":"Bla\u017e Meden","orcid":"https://orcid.org/0000-0002-1690-4798","observed_orcids":["https://orcid.org/0000-0002-1690-4798"]},"institutions":[{"id":"https://openalex.org/I153976015","display_name":"University of Ljubljana","ror":"https://ror.org/05njb9z20","country_code":"SI","type":"education","lineage":["https://openalex.org/I153976015"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Bla\u017e Meden","raw_affiliation_strings":["Faculty of Computer and Information Science, University of Ljubljana, SI-1000 Ljubljana, Slovenia"],"raw_orcid":"https://orcid.org/0000-0002-1690-4798","affiliations":[{"raw_affiliation_string":"Faculty of Computer and Information Science, University of Ljubljana, SI-1000 Ljubljana, Slovenia","institution_ids":["https://openalex.org/I153976015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008809776","display_name":"\u017diga Emer\u0161i\u010d","orcid":"https://orcid.org/0000-0002-3726-9404","observed_orcids":["https://orcid.org/0000-0002-3726-9404"]},"institutions":[{"id":"https://openalex.org/I153976015","display_name":"University of Ljubljana","ror":"https://ror.org/05njb9z20","country_code":"SI","type":"education","lineage":["https://openalex.org/I153976015"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"\u017diga Emer\u0161i\u010d","raw_affiliation_strings":["Faculty of Computer and Information Science, University of Ljubljana, SI-1000 Ljubljana, Slovenia"],"raw_orcid":"https://orcid.org/0000-0002-3726-9404","affiliations":[{"raw_affiliation_string":"Faculty of Computer and Information Science, University of Ljubljana, SI-1000 Ljubljana, Slovenia","institution_ids":["https://openalex.org/I153976015"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041138233"],"corresponding_institution_ids":["https://openalex.org/I10232997"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2728},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2728},"fwci":5.5724,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.973018,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"13","issue":"9","first_page":"1726","last_page":"1726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9926999807357788,"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":0.9926999807357788,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.002099999925121665,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0017000000225380063,"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/image-captioning","display_name":"image captioning","score":0.7979999780654907},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"speech synthesis","score":0.8109999895095825},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.8759999871253967},{"id":"https://openalex.org/keywords/encoder-decoder-architecture","display_name":"encoder-decoder architecture","score":0.8370000123977661},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.7609999775886536},{"id":"https://openalex.org/keywords/adversarial-machine-learning","display_name":"adversarial learning","score":0.9940000176429749},{"id":"https://openalex.org/keywords/accessibility","display_name":"accessibility","score":0.6859999895095825}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8363070487976074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827261686325073},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5361796021461487},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49491971731185913},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4888579249382019},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.47119614481925964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4573700726032257},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4391118884086609},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4383160471916199},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4364761412143707},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37785494327545166},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25520822405815125},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/electronics13091726","doi":"https://doi.org/10.3390/electronics13091726","is_oa":true,"landing_page_url":"https://doi.org/10.3390/electronics13091726","pdf_url":"https://www.mdpi.com/2079-9292/13/9/1726/pdf?version=1714464728","source":{"id":"https://openalex.org/S4210202905","display_name":"Electronics","issn_l":"2079-9292","issn":["2079-9292"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/electronics13091726","doi":"https://doi.org/10.3390/electronics13091726","is_oa":true,"landing_page_url":"https://doi.org/10.3390/electronics13091726","pdf_url":"https://www.mdpi.com/2079-9292/13/9/1726/pdf?version=1714464728","source":{"id":"https://openalex.org/S4210202905","display_name":"Electronics","issn_l":"2079-9292","issn":["2079-9292"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronics","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396510248.pdf","grobid_xml":"https://content.openalex.org/works/W4396510248.grobid-xml"},"referenced_works_count":83,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W133559434","https://openalex.org/W175280642","https://openalex.org/W200094172","https://openalex.org/W344150399","https://openalex.org/W1494198834","https://openalex.org/W1514535095","https://openalex.org/W1570629387","https://openalex.org/W1576227399","https://openalex.org/W1600722501","https://openalex.org/W1861492603","https://openalex.org/W1895989618","https://openalex.org/W2001538905","https://openalex.org/W2056191164","https://openalex.org/W2102003408","https://openalex.org/W2109586012","https://openalex.org/W2112955368","https://openalex.org/W2113899393","https://openalex.org/W2129142580","https://openalex.org/W2134973740","https://openalex.org/W2137010615","https://openalex.org/W2145575463","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2169153920","https://openalex.org/W2185175083","https://openalex.org/W2294797155","https://openalex.org/W2463955103","https://openalex.org/W2515943672","https://openalex.org/W2560313346","https://openalex.org/W2566119519","https://openalex.org/W2604178507","https://openalex.org/W2607151106","https://openalex.org/W2626778328","https://openalex.org/W2788357188","https://openalex.org/W2806733747","https://openalex.org/W2886641317","https://openalex.org/W2901988662","https://openalex.org/W2902440562","https://openalex.org/W2956612537","https://openalex.org/W2962968835","https://openalex.org/W2963062932","https://openalex.org/W2963177331","https://openalex.org/W2963609956","https://openalex.org/W2963902314","https://openalex.org/W2972359262","https://openalex.org/W2990818246","https://openalex.org/W2992526251","https://openalex.org/W2996011278","https://openalex.org/W2997208288","https://openalex.org/W3007456797","https://openalex.org/W3007780968","https://openalex.org/W3009205145","https://openalex.org/W3013137071","https://openalex.org/W3018385214","https://openalex.org/W3034429116","https://openalex.org/W3095909497","https://openalex.org/W3095990227","https://openalex.org/W3114436296","https://openalex.org/W3122720459","https://openalex.org/W3131702728","https://openalex.org/W3142087749","https://openalex.org/W3155217823","https://openalex.org/W3155727213","https://openalex.org/W3160100917","https://openalex.org/W3165571294","https://openalex.org/W3169874582","https://openalex.org/W3172387178","https://openalex.org/W3197064454","https://openalex.org/W3198533616","https://openalex.org/W3199400376","https://openalex.org/W3206387123","https://openalex.org/W4206865574","https://openalex.org/W4230559685","https://openalex.org/W4289600032","https://openalex.org/W4292455922","https://openalex.org/W4297570641","https://openalex.org/W4299541593","https://openalex.org/W4320013936","https://openalex.org/W4389959945","https://openalex.org/W6640200569","https://openalex.org/W6676497082","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4403765453","https://openalex.org/W4411468720","https://openalex.org/W4407932368","https://openalex.org/W7139029173","https://openalex.org/W4406267328","https://openalex.org/W4412167580","https://openalex.org/W4401018201","https://openalex.org/W7171529157","https://openalex.org/W4401016775","https://openalex.org/W7213560228"],"abstract_inverted_index":{"In":[0,81],"recent":[1],"years,":[2],"there":[3],"has":[4,66],"been":[5,105],"increasing":[6],"interest":[7],"in":[8,161,194],"the":[9,23,58,75,122,135,156,166,176,208,211],"conversion":[10,91,103],"of":[11,25,43,54,60,77,89,95,124,138,155,170,178,213,231],"images":[12,44],"into":[13,49],"audio":[14,130,219],"descriptions.":[15],"This":[16,65,149],"is":[17,57,127,146],"a":[18,86,152,191],"field":[19,56],"that":[20],"lies":[21],"at":[22],"intersection":[24],"Computer":[26],"Vision":[27],"(CV)":[28],"and":[29,34,45,74,100,118,158,164,168,186,201,217],"Natural":[30],"Language":[31],"Processing":[32],"(NLP),":[33],"it":[35],"involves":[36],"various":[37,179],"tasks,":[38],"including":[39],"creating":[40,139],"textual":[41],"descriptions":[42,131,145],"converting":[46],"them":[47],"directly":[48],"auditory":[50,229],"representations.":[51],"Another":[52],"aspect":[53],"this":[55,82,125],"synthesis":[59],"natural":[61,143,216],"speech":[62,98],"from":[63,107,132,142],"text.":[64],"significant":[67],"potential":[68,212],"to":[69,111],"improve":[70],"accessibility,":[71],"user":[72],"experience,":[73],"applications":[76],"Artificial":[78],"Intelligence":[79],"(AI).":[80],"article,":[83],"we":[84],"reviewed":[85],"wide":[87],"range":[88],"image-to-audio":[90],"techniques.":[92],"Various":[93],"aspects":[94],"image":[96],"captioning,":[97],"synthesis,":[99],"direct":[101,222],"image-to-speech":[102,223],"have":[104],"explored,":[106],"fundamental":[108],"encoder\u2013decoder":[109],"architectures":[110],"more":[112,215],"advanced":[113],"methods":[114],"such":[115,181],"as":[116,182],"transformers":[117],"adversarial":[119],"learning.":[120],"Although":[121],"focus":[123],"review":[126],"on":[128],"synthesizing":[129],"visual":[133,140,232],"data,":[134],"reverse":[136],"task":[137],"content":[141],"language":[144],"also":[147],"covered.":[148],"study":[150,174],"provides":[151],"comprehensive":[153],"overview":[154],"techniques":[157],"methodologies":[159],"used":[160],"these":[162],"fields":[163],"highlights":[165],"strengths":[167],"weaknesses":[169],"each":[171],"approach.":[172],"The":[173,205],"emphasizes":[175],"importance":[177],"datasets,":[180],"MS":[183],"COCO,":[184],"LibriTTS,":[185],"VizWiz":[187],"Captions,":[188],"which":[189],"play":[190],"critical":[192],"role":[193],"training":[195],"models,":[196],"evaluating":[197],"them,":[198],"promoting":[199],"inclusivity,":[200],"solving":[202],"real-world":[203],"problems.":[204],"implications":[206],"for":[207,227],"future":[209],"suggest":[210],"generating":[214],"contextualized":[218],"descriptions,":[220],"whereas":[221],"tasks":[224],"provide":[225],"opportunities":[226],"intuitive":[228],"representations":[230],"content.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2024-05-01T00:00:00"}
