{"id":"https://openalex.org/W4385823125","doi":"https://doi.org/10.21437/interspeech.2023-1082","title":"Adapting Language-Audio Models as Few-Shot Audio Learners","display_name":"Adapting Language-Audio Models as Few-Shot Audio Learners","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823125","doi":"https://doi.org/10.21437/interspeech.2023-1082"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1082","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/88692/2/Benetos%20Adapting%20Language-Audio%20Models%20as%20Few-Shot%20Audio%20Learners%202023%20Accepted.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100526373","display_name":"Jinhua Liang","orcid":"https://orcid.org/0000-0002-4570-0735"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinhua Liang","raw_affiliation_strings":["\u22c6 Centre for Digital Music, Queen Mary University of London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u22c6 Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080214850","display_name":"Xubo Liu","orcid":"https://orcid.org/0000-0002-2558-0959"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP)","institution_ids":["https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haohe Liu","raw_affiliation_strings":["\u22c6 Centre for Digital Music, Queen Mary University of London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u22c6 Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027304029","display_name":"Huy P. Phan","orcid":"https://orcid.org/0000-0002-3066-4647"},"institutions":[{"id":"https://openalex.org/I125680101","display_name":"Turing Institute","ror":"https://ror.org/02x2mw849","country_code":"GB","type":"facility","lineage":["https://openalex.org/I125680101"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP)","Amazon Alexa \u2021 The Alan Turing Institute, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP)","institution_ids":["https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Amazon Alexa \u2021 The Alan Turing Institute, UK","institution_ids":["https://openalex.org/I125680101","https://openalex.org/I4210123934","https://openalex.org/I4210128584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":"https://orcid.org/0000-0002-6820-6764"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["\u22c6 Centre for Digital Music, Queen Mary University of London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u22c6 Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP)","institution_ids":["https://openalex.org/I4210121626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP)","institution_ids":["https://openalex.org/I4210121626"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.8806999921798706,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.8806999921798706,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"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":0.7746566534042358},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6176261305809021},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5404684543609619},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.41198667883872986},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3340049684047699}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746566534042358},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6176261305809021},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5404684543609619},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.41198667883872986},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3340049684047699},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-1082","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/88692","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/88692","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/88692/2/Benetos%20Adapting%20Language-Audio%20Models%20as%20Few-Shot%20Audio%20Learners%202023%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/88692","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/88692","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/88692/2/Benetos%20Adapting%20Language-Audio%20Models%20as%20Few-Shot%20Audio%20Learners%202023%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G3512924261","display_name":"DTP 2020-2021 Queen Mary University of London","funder_award_id":"EP/T518086/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8857457899","display_name":null,"funder_award_id":"EP/T019751/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320311061","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823125.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2526050071","https://openalex.org/W2601450892","https://openalex.org/W2884535146","https://openalex.org/W2963341924","https://openalex.org/W3091905774","https://openalex.org/W3166396011","https://openalex.org/W3176445421","https://openalex.org/W3190965961","https://openalex.org/W3198377975","https://openalex.org/W4205236539","https://openalex.org/W4205689591","https://openalex.org/W4225323055","https://openalex.org/W4226442948","https://openalex.org/W4312047065","https://openalex.org/W4312310776","https://openalex.org/W4313175608","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4385245566","https://openalex.org/W4386076681"],"related_works":["https://openalex.org/W2355862304","https://openalex.org/W2356108042","https://openalex.org/W2030250808","https://openalex.org/W2376796979","https://openalex.org/W2379418341","https://openalex.org/W2380054981","https://openalex.org/W2393110101","https://openalex.org/W2379285345","https://openalex.org/W2331065455","https://openalex.org/W4255510578"],"abstract_inverted_index":{"Contrastive":[0],"language-audio":[1],"pretraining":[2],"(CLAP)":[3],"has":[4],"become":[5],"a":[6,35,72,80,95,102,119],"new":[7],"paradigm":[8],"to":[9,39,63,76,100,110,142],"learn":[10,78],"audio":[11,42,109],"concepts":[12],"with":[13,32,44,79],"audio-text":[14],"pairs.":[15],"CLAP":[16,31],"models":[17],"have":[18],"shown":[19],"unprecedented":[20],"performance":[21],"as":[22,55,118],"zero-shot":[23,90],"classifiers":[24],"on":[25],"downstream":[26],"tasks.":[27],"To":[28],"further":[29],"adapt":[30],"domain-specific":[33],"knowledge,":[34],"popular":[36],"method":[37],"is":[38,50,60],"finetune":[40],"its":[41],"encoder":[43],"available":[45],"labelled":[46,105],"examples.":[47],"However,":[48],"this":[49,68],"challenging":[51],"in":[52,135],"low-shot":[53],"scenarios,":[54],"the":[56,64,87],"amount":[57],"of":[58,83,104],"annotations":[59],"limited":[61],"compared":[62],"model":[65,98],"size.":[66],"In":[67],"work,":[69],"we":[70,93,114],"introduce":[71],"Training-efficient":[73],"(Treff)":[74],"adapter":[75,125,131],"rapidly":[77],"small":[81],"set":[82,103],"examples":[84,106],"while":[85],"maintaining":[86],"capacity":[88],"for":[89],"classification.":[91],"First,":[92],"propose":[94],"cross-attention":[96],"linear":[97],"(CALM)":[99],"map":[101],"and":[107,138],"test":[108,111],"labels.":[112],"Second,":[113],"find":[115],"initialising":[116],"CALM":[117],"cosine":[120],"measurement":[121],"improves":[122],"our":[123],"Treff":[124,130],"even":[126],"without":[127],"training.":[128],"The":[129],"outperforms":[132],"metric-based":[133],"methods":[134],"few-shot":[136],"settings":[137],"yields":[139],"competitive":[140],"results":[141],"fully-supervised":[143],"methods.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
