{"id":"https://openalex.org/W4319862477","doi":"https://doi.org/10.1109/slt54892.2023.10022954","title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","display_name":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862477","doi":"https://doi.org/10.1109/slt54892.2023.10022954"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022954","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/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":[{"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":"Heng-Jui Chang","raw_affiliation_strings":["National Taiwan University","MIT CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","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":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"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":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The 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":1.2275,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.80620805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"715","last_page":"722"},"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/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9962000250816345,"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":0.8644802570343018},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7403520345687866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6725541353225708},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.566286027431488},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.556280255317688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5541245937347412},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5484566688537598},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5168276429176331},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5043419599533081},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.457922101020813},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.4436776340007782},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44106635451316833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8644802570343018},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7403520345687866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6725541353225708},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.566286027431488},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.556280255317688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5541245937347412},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5484566688537598},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5168276429176331},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5043419599533081},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.457922101020813},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.4436776340007782},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44106635451316833},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022954","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320316620","display_name":"Amazon Catalyst","ror":"https://ror.org/04mv4n011"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2242818861","https://openalex.org/W2962862718","https://openalex.org/W2963330681","https://openalex.org/W2963902314","https://openalex.org/W2964099072","https://openalex.org/W2972892814","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2973135958","https://openalex.org/W2982223350","https://openalex.org/W2988907666","https://openalex.org/W3015213852","https://openalex.org/W3015300171","https://openalex.org/W3041561163","https://openalex.org/W3094626712","https://openalex.org/W3097286738","https://openalex.org/W3157861865","https://openalex.org/W3161204797","https://openalex.org/W3174311593","https://openalex.org/W3176445421","https://openalex.org/W3189296823","https://openalex.org/W3196698946","https://openalex.org/W3197467690","https://openalex.org/W3197580070","https://openalex.org/W3198858531","https://openalex.org/W3200287550","https://openalex.org/W3203140070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4221161768","https://openalex.org/W4224821750","https://openalex.org/W4224875474","https://openalex.org/W4226033575","https://openalex.org/W4226380987","https://openalex.org/W4281492411","https://openalex.org/W4284898017","https://openalex.org/W4285110637","https://openalex.org/W4285250921","https://openalex.org/W4286359908","https://openalex.org/W4297808394","https://openalex.org/W4319862670","https://openalex.org/W6739901393","https://openalex.org/W6756706075","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6791353385","https://openalex.org/W6795952400","https://openalex.org/W6803675045","https://openalex.org/W6810673746"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2184127972","https://openalex.org/W596245619","https://openalex.org/W2550171623","https://openalex.org/W2964829415","https://openalex.org/W2343205865","https://openalex.org/W642007152","https://openalex.org/W2105439218","https://openalex.org/W2341426843","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Data-driven":[0],"speech":[1,17,29,36],"processing":[2],"models":[3,37],"usually":[4],"perform":[5],"well":[6],"with":[7,55],"a":[8,25],"large":[9],"amount":[10],"of":[11],"text":[12,31],"supervision,":[13],"but":[14],"collecting":[15],"transcribed":[16],"data":[18],"is":[19],"costly.":[20],"Therefore,":[21],"we":[22],"propose":[23],"Speech-CLIP,":[24],"novel":[26],"framework":[27],"bridging":[28],"and":[30,45,52,65],"through":[32],"images":[33,51],"to":[34],"enhance":[35],"without":[38,70],"transcriptions.":[39,74],"We":[40],"leverage":[41],"state-of-the-art":[42,61],"pre-trained":[43],"HuBERT":[44],"CLIP,":[46],"aligning":[47],"them":[48],"via":[49],"paired":[50],"spoken":[53],"captions":[54],"minimal":[56],"fine-tuning.":[57],"SpeechCLIP":[58,76],"outperforms":[59],"prior":[60],"on":[62],"image-speech":[63],"retrieval":[64,69],"performs":[66],"zero-shot":[67],"speech-text":[68],"direct":[71],"supervision":[72],"from":[73,83],"Moreover,":[75],"can":[77],"directly":[78],"retrieve":[79],"semantically":[80],"related":[81],"keywords":[82],"speech.":[84]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
