{"id":"https://openalex.org/W3176445421","doi":"https://doi.org/10.1109/icassp43922.2022.9747631","title":"Audioclip: Extending Clip to Image, Text and Audio","display_name":"Audioclip: Extending Clip to Image, Text and Audio","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3176445421","doi":"https://doi.org/10.1109/icassp43922.2022.9747631","mag":"3176445421"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747631","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5051399221","display_name":"Andrey Guzhov","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Andrey Guzhov","raw_affiliation_strings":["Deutsches Forschungszentrum für Künstliche Intelligenz GmbH,Kaiserslautern,Germany"],"affiliations":[{"raw_affiliation_string":"Deutsches Forschungszentrum für Künstliche Intelligenz GmbH,Kaiserslautern,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029509133","display_name":"Federico Raue","orcid":"https://orcid.org/0000-0002-8604-6207"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Federico Raue","raw_affiliation_strings":["Deutsches Forschungszentrum für Künstliche Intelligenz GmbH,Kaiserslautern,Germany"],"affiliations":[{"raw_affiliation_string":"Deutsches Forschungszentrum für Künstliche Intelligenz GmbH,Kaiserslautern,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019899855","display_name":"J.J. van Hees","orcid":"https://orcid.org/0000-0002-0084-8998"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jorn Hees","raw_affiliation_strings":["Deutsches Forschungszentrum für Künstliche Intelligenz GmbH,Kaiserslautern,Germany"],"affiliations":[{"raw_affiliation_string":"Deutsches Forschungszentrum für Künstliche Intelligenz GmbH,Kaiserslautern,Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101904182","display_name":"Andreas Dengel","orcid":"https://orcid.org/0000-0002-6100-8255"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Dengel","raw_affiliation_strings":["Deutsches Forschungszentrum für Künstliche Intelligenz GmbH,Kaiserslautern,Germany"],"affiliations":[{"raw_affiliation_string":"Deutsches Forschungszentrum für Künstliche Intelligenz GmbH,Kaiserslautern,Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051399221"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":31.1116,"has_fulltext":false,"cited_by_count":269,"citation_normalized_percentile":{"value":0.99842619,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"976","last_page":"980"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9817000031471252,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8082341551780701},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6909766793251038},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.573991596698761},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5731393098831177},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5693812966346741},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5436391830444336},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4950834810733795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48839062452316284},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.4796717166900635},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4721177816390991},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44340649247169495},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3731570243835449},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3408662676811218},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07533273100852966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082341551780701},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6909766793251038},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.573991596698761},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5731393098831177},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5693812966346741},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5436391830444336},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4950834810733795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48839062452316284},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4796717166900635},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4721177816390991},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44340649247169495},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3731570243835449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3408662676811218},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07533273100852966},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747631","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1605494325","https://openalex.org/W1972567154","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2086161653","https://openalex.org/W2108598243","https://openalex.org/W2128532956","https://openalex.org/W2194775991","https://openalex.org/W2509065397","https://openalex.org/W2531409750","https://openalex.org/W2593116425","https://openalex.org/W2593451766","https://openalex.org/W2619697695","https://openalex.org/W2626778328","https://openalex.org/W2745357708","https://openalex.org/W2768188490","https://openalex.org/W2785809060","https://openalex.org/W2914312680","https://openalex.org/W2930959424","https://openalex.org/W2945761034","https://openalex.org/W2972247414","https://openalex.org/W2998351764","https://openalex.org/W3034886385","https://openalex.org/W3037309139","https://openalex.org/W3040498734","https://openalex.org/W3045062880","https://openalex.org/W3094502228","https://openalex.org/W3098357269","https://openalex.org/W3135367836","https://openalex.org/W3138521398","https://openalex.org/W3146639881","https://openalex.org/W3154596443","https://openalex.org/W3157916917","https://openalex.org/W3158553615","https://openalex.org/W3166396011","https://openalex.org/W3173388686","https://openalex.org/W3180463990","https://openalex.org/W3196974791","https://openalex.org/W3201065055","https://openalex.org/W4286582832","https://openalex.org/W6643326691","https://openalex.org/W6745930336","https://openalex.org/W6747045456","https://openalex.org/W6748400442","https://openalex.org/W6779503413","https://openalex.org/W6780294235","https://openalex.org/W6781150751","https://openalex.org/W6791353385","https://openalex.org/W6792052185","https://openalex.org/W6793728465","https://openalex.org/W6840046036"],"related_works":["https://openalex.org/W2354322770","https://openalex.org/W3000097931","https://openalex.org/W4214877189","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W2074502265","https://openalex.org/W4239268388","https://openalex.org/W1924837940","https://openalex.org/W2379407973","https://openalex.org/W4243305035"],"abstract_inverted_index":{"The":[0],"rapidly":[1],"evolving":[2],"field":[3],"of":[4,13,40,97,130,138,145],"sound":[5],"classification":[6,74],"has":[7],"greatly":[8],"benefited":[9],"from":[10],"the":[11,17,29,41,54,61,65,85,113,117,128,135,139,143],"methods":[12],"other":[14],"domains.":[15],"Today,":[16],"trend":[18],"is":[19,149],"to":[20,49,71],"fuse":[21],"domain-specific":[22],"tasks":[23],"and":[24,51,75,91,102,122],"approaches":[25],"together,":[26],"which":[27],"provides":[28],"community":[30],"with":[31],"new":[32,81,110],"outstanding":[33],"models.We":[34],"present":[35],"AudioCLIP":[36],"\u2013":[37],"an":[38],"extension":[39],"CLIP":[42,66],"model":[43,59],"that":[44],"handles":[45],"audio":[46],"in":[47,84,112],"addition":[48],"text":[50],"images.":[52],"Utilizing":[53],"AudioSet":[55],"dataset,":[56],"our":[57,147],"proposed":[58,140],"incorporates":[60],"ESResNeXt":[62],"audio-model":[63],"into":[64],"framework,":[67],"thus":[68],"enabling":[69],"it":[70,108],"perform":[72],"multimodal":[73],"keeping":[76],"CLIP\u2019s":[77],"zero-shot":[78,114],"capabilities.AudioCLIP":[79],"achieves":[80],"state-of-the-art":[82],"results":[83],"Environmental":[86],"Sound":[87],"Classification":[88],"(ESC)":[89],"task":[90],"out-performs":[92],"others":[93],"by":[94],"reaching":[95],"accuracies":[96],"97.15":[98],"%":[99,104,121],"on":[100,105,116,134],"ESC-50":[101],"90.07":[103],"UrbanSound8K.":[106],"Further,":[107],"sets":[109],"baselines":[111],"ESC-task":[115],"same":[118],"datasets":[119],"(69.40":[120],"68.78":[123],"%,":[124],"respectively).We":[125],"also":[126],"asses":[127],"influence":[129],"different":[131],"training":[132],"setups":[133],"final":[136],"performance":[137],"model.":[141],"For":[142],"sake":[144],"reproducibility,":[146],"code":[148],"published.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":94},{"year":2024,"cited_by_count":85},{"year":2023,"cited_by_count":57},{"year":2022,"cited_by_count":20}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}