{"id":"https://openalex.org/W3196698946","doi":"https://doi.org/10.21437/interspeech.2021-96","title":"Talk, Don’t Write: A Study of Direct Speech-Based Image Retrieval","display_name":"Talk, Don’t Write: A Study of Direct Speech-Based Image Retrieval","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196698946","doi":"https://doi.org/10.21437/interspeech.2021-96","mag":"3196698946"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-96","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-96","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-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/A5053704856","display_name":"Ramon Sanabria","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ramon Sanabria","raw_affiliation_strings":["The University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064711844","display_name":"Austin Waters","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin Waters","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048931310","display_name":"Jason Baldridge","orcid":"https://orcid.org/0000-0002-4712-1841"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Baldridge","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5822,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.68674699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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":0.9965999722480774,"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/T11309","display_name":"Music and Audio Processing","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9782999753952026,"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/computer-science","display_name":"Computer science","score":0.6989988088607788},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5707381367683411},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5361001491546631},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5050056576728821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49966931343078613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3702463209629059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6989988088607788},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5707381367683411},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5361001491546631},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5050056576728821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49966931343078613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3702463209629059}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-96","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-96","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W2119775030","https://openalex.org/W2137010615","https://openalex.org/W2556930864","https://openalex.org/W2586148577","https://openalex.org/W2593116425","https://openalex.org/W2796315435","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2901894078","https://openalex.org/W2923959898","https://openalex.org/W2927673779","https://openalex.org/W2955425717","https://openalex.org/W2962753610","https://openalex.org/W2963525826","https://openalex.org/W2964001192","https://openalex.org/W2964099072","https://openalex.org/W2971709506","https://openalex.org/W2972345028","https://openalex.org/W2973049979","https://openalex.org/W2988823324","https://openalex.org/W2988907666","https://openalex.org/W2989358187","https://openalex.org/W2995680346","https://openalex.org/W2998649947","https://openalex.org/W3005680577","https://openalex.org/W3015300171","https://openalex.org/W3095670406","https://openalex.org/W3100813302","https://openalex.org/W3155594712","https://openalex.org/W3197828817","https://openalex.org/W4287757663","https://openalex.org/W4297826211","https://openalex.org/W4394453761"],"related_works":["https://openalex.org/W2087793626","https://openalex.org/W2052697133","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W3177930984","https://openalex.org/W2951359407","https://openalex.org/W2124566234","https://openalex.org/W3136979370","https://openalex.org/W3192589309"],"abstract_inverted_index":{"Speech-based":[0],"image":[1],"retrieval":[2,17,26],"has":[3],"been":[4],"studied":[5],"as":[6],"a":[7],"proxy":[8],"for":[9,105,112],"joint":[10],"representation":[11],"learning,":[12],"usually":[13],"without":[14],"emphasis":[15],"on":[16],"itself.As":[18],"such,":[19],"it":[20],"is":[21,130],"unclear":[22],"how":[23],"well":[24],"speech-based":[25,119],"can":[27,121],"work":[28],"in":[29,32,77],"practice":[30],"-both":[31],"an":[33],"absolute":[34],"sense":[35],"and":[36,55,65,68,84,108],"versus":[37],"alternative":[38],"strategies":[39],"that":[40],"combine":[41],"automatic":[42],"speech":[43,76,129],"recognition":[44],"(ASR)":[45],"with":[46],"strong":[47],"text":[48],"encoders.In":[49],"this":[50],"work,":[51],"we":[52],"extensively":[53],"study":[54],"expand":[56],"choices":[57],"of":[58,75,95],"encoder":[59],"architectures,":[60],"training":[61],"methodology":[62],"(including":[63],"unimodal":[64],"multimodal":[66],"pretraining),":[67],"other":[69],"factors.Our":[70],"experiments":[71],"cover":[72],"different":[73],"types":[74],"three":[78],"datasets:":[79],"Flickr":[80,106],"Audio,":[81,83],"Places":[82,113],"Localized":[85],"Narratives.Our":[86],"best":[87,118],"model":[88],"configuration":[89],"achieves":[90],"large":[91],"gains":[92],"over":[93],"state":[94],"the":[96],"art,":[97],"e.g.,":[98],"pushing":[99],"recall-atone":[100],"from":[101],"21.8%":[102],"to":[103,110,136],"33.2%":[104],"Audio":[107],"27.6%":[109],"53.4%":[111],"Audio.We":[114],"also":[115],"show":[116],"our":[117],"models":[120],"match":[122],"or":[123,133],"exceed":[124],"cascaded":[125],"ASR-to-text":[126],"encoding":[127],"when":[128],"spontaneous,":[131],"accented,":[132],"otherwise":[134],"hard":[135],"automatically":[137],"transcribe.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}