{"id":"https://openalex.org/W4372267276","doi":"https://doi.org/10.1109/icassp49357.2023.10096882","title":"M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval","display_name":"M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267276","doi":"https://doi.org/10.1109/icassp49357.2023.10096882"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096882","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5084236961","display_name":"Layne Berry","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Layne Berry","raw_affiliation_strings":["University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053466746","display_name":"Yi-Jen Shih","orcid":"https://orcid.org/0000-0003-3481-3117"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Jen Shih","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110941853","display_name":"Hsuan-Fu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsuan-Fu Wang","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078976109","display_name":"Heng-Jui Chang","orcid":"https://orcid.org/0000-0002-1690-2610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng-Jui Chang","raw_affiliation_strings":["MIT CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004717608","display_name":"David Harwath","orcid":"https://orcid.org/0000-0003-0206-0253"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Harwath","raw_affiliation_strings":["University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8982,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.75770368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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/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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987999796867371,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9919999837875366,"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/computer-science","display_name":"Computer science","score":0.8617466688156128},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.699481189250946},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6191006898880005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5454680323600769},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5436716079711914},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4716334044933319},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43721258640289307},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12495386600494385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8617466688156128},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.699481189250946},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6191006898880005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5454680323600769},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5436716079711914},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4716334044933319},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43721258640289307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12495386600494385},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096882","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2134670479","https://openalex.org/W2250384498","https://openalex.org/W2277195237","https://openalex.org/W2556930864","https://openalex.org/W2920166246","https://openalex.org/W2950133079","https://openalex.org/W2962862718","https://openalex.org/W2963330681","https://openalex.org/W2964099072","https://openalex.org/W2973135958","https://openalex.org/W2988907666","https://openalex.org/W3015300171","https://openalex.org/W3094502228","https://openalex.org/W3095881291","https://openalex.org/W3166396011","https://openalex.org/W3174311593","https://openalex.org/W3196694757","https://openalex.org/W3200287550","https://openalex.org/W3200356107","https://openalex.org/W3209059054","https://openalex.org/W4319862477","https://openalex.org/W4385245566","https://openalex.org/W6639102338","https://openalex.org/W6679792166","https://openalex.org/W6694395031","https://openalex.org/W6729977899","https://openalex.org/W6739901393","https://openalex.org/W6750194919","https://openalex.org/W6756706075","https://openalex.org/W6760188208","https://openalex.org/W6775566795","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6801213118","https://openalex.org/W6801926475","https://openalex.org/W6845527703"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W2340870721","https://openalex.org/W2358318464","https://openalex.org/W2979236518","https://openalex.org/W3091955004"],"abstract_inverted_index":{"This":[0],"work":[1],"investigates":[2],"the":[3,23,67,78],"use":[4],"of":[5,70],"large-scale,":[6],"English-only":[7,68],"pre-trained":[8,79],"models":[9,35,80,89],"(CLIP":[10],"and":[11,39,58,62,72,74,95,99],"HuBERT)":[12],"for":[13,36,93],"multilingual":[14],"image-speech":[15,19],"retrieval.":[16],"For":[17],"non-English":[18,63],"retrieval,":[20,102],"we":[21,85],"outperform":[22],"current":[24],"state-of-the-art":[25],"performance":[26,59],"by":[27],"a":[28,41],"wide":[29],"margin":[30],"both":[31],"when":[32],"training":[33],"separate":[34],"each":[37],"language,":[38],"with":[40],"single":[42],"model":[43,56],"which":[44],"processes":[45],"speech":[46],"in":[47,55],"all":[48],"three":[49],"languages.":[50],"We":[51],"identify":[52],"key":[53],"differences":[54],"behavior":[57],"between":[60],"English":[61],"settings,":[64],"attributable":[65],"to":[66],"pre-training":[69],"CLIP":[71],"HuBERT,":[73],"investigate":[75],"how":[76],"fine-tuning":[77],"impacts":[81],"these":[82],"differences.":[83],"Finally,":[84],"show":[86],"that":[87],"our":[88],"can":[90],"be":[91],"used":[92],"mono-":[94],"cross-lingual":[96,100],"speech-text":[97,109],"retrieval":[98],"speech-speech":[101,111],"despite":[103],"never":[104],"having":[105],"seen":[106],"any":[107],"parallel":[108],"or":[110],"data":[112],"during":[113],"training.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}