{"id":"https://openalex.org/W4408355048","doi":"https://doi.org/10.1109/icassp49660.2025.10890484","title":"Bridging the Modality Gap for Speech-image Retrieval with Text Supervision","display_name":"Bridging the Modality Gap for Speech-image Retrieval with Text Supervision","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355048","doi":"https://doi.org/10.1109/icassp49660.2025.10890484"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5028185223","display_name":"Yuting Yang","orcid":"https://orcid.org/0000-0003-4260-4550"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Yang","raw_affiliation_strings":["Netease,Yidun AI Lab,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netease,Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049844296","display_name":"Lifeng Zhou","orcid":"https://orcid.org/0000-0001-5479-3681"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifeng Zhou","raw_affiliation_strings":["Netease,Yidun AI Lab,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netease,Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697204","display_name":"Yuke Li","orcid":"https://orcid.org/0009-0000-7282-8964"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuke Li","raw_affiliation_strings":["Netease,Yidun AI Lab,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netease,Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052807371","display_name":"Guodong Ma","orcid":"https://orcid.org/0009-0005-1910-7494"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guodong Ma","raw_affiliation_strings":["Netease,Yidun AI Lab,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netease,Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01686113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9625999927520752,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9625999927520752,"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/bridging","display_name":"Bridging (networking)","score":0.905992865562439},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7778739929199219},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6177626252174377},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6094605922698975},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5218885540962219},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45121127367019653},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4477262794971466},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44520798325538635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4291403591632843},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07420194149017334}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.905992865562439},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778739929199219},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6177626252174377},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6094605922698975},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5218885540962219},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45121127367019653},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4477262794971466},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44520798325538635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4291403591632843},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07420194149017334}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2481240925","https://openalex.org/W2766219058","https://openalex.org/W2962862718","https://openalex.org/W2963250244","https://openalex.org/W2963341956","https://openalex.org/W2973049979","https://openalex.org/W3097882114","https://openalex.org/W3174311593","https://openalex.org/W3196698946","https://openalex.org/W3197580070","https://openalex.org/W3200287550","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4285250921","https://openalex.org/W4286611278","https://openalex.org/W4319862477","https://openalex.org/W4372269205","https://openalex.org/W4385823492","https://openalex.org/W4401597893","https://openalex.org/W4402112006","https://openalex.org/W6675365184","https://openalex.org/W6780218876","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6810007534","https://openalex.org/W6810505583","https://openalex.org/W6811013733","https://openalex.org/W6847363464","https://openalex.org/W6849177959"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214","https://openalex.org/W2084768720","https://openalex.org/W2043010663","https://openalex.org/W4248308508"],"abstract_inverted_index":{"In":[0,33],"recent":[1],"years,":[2],"while":[3],"the":[4,21,44,83,114,117,121,131,137,141,146],"performance":[5,147],"of":[6,17,116,148],"speech-image":[7,26,74,99,149],"retrieval":[8,27,100],"has":[9],"improved":[10],"significantly,":[11],"it":[12],"still":[13],"lags":[14],"behind":[15],"that":[16,113,140],"image-text":[18],"retrieval.":[19,150],"Leveraging":[20],"text":[22,40,88],"modality":[23,89],"to":[24,38,42,86,96,130],"enhance":[25,98],"remains":[28],"a":[29,66],"promising":[30],"research":[31],"direction.":[32],"this":[34,79],"paper,":[35],"we":[36,91],"propose":[37],"leverage":[39],"supervision":[41],"facilitate":[43],"alignment":[45],"between":[46],"speech":[47,55],"and":[48,73,110,126],"image":[49],"feature":[50],"spaces":[51],"via":[52],"an":[53,93],"automatic":[54],"recognition":[56],"(ASR)":[57],"auxiliary":[58],"task.":[59],"Specifically,":[60],"our":[61],"model":[62],"is":[63],"trained":[64],"with":[65],"multi-task":[67],"learning":[68,76],"framework,":[69],"which":[70],"combines":[71],"ASR":[72,84,118],"contrastive":[75],"tasks.":[77],"On":[78],"basis,":[80],"benefiting":[81],"from":[82],"module":[85],"obtain":[87],"information,":[90],"introduce":[92],"ensemble":[94,142],"mechanism":[95,143],"further":[97,144],"performance.":[101],"Experimental":[102],"results":[103,138],"on":[104],"two":[105],"publicly":[106],"available":[107],"datasets":[108],"Flickr8k":[109],"SpokenCOCO":[111],"indicate":[112],"introduction":[115],"task":[119],"improves":[120],"mean":[122],"R@1":[123],"by":[124],"2.7%":[125],"2%,":[127],"respectively,":[128],"compared":[129],"previous":[132],"state-of-the-art":[133],"(SOTA)":[134],"method.":[135],"Furthermore,":[136],"demonstrate":[139],"enhances":[145]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}