{"id":"https://openalex.org/W4387760932","doi":"https://doi.org/10.1109/waspaa58266.2023.10248180","title":"Unsupervised Improvement of Audio-Text Cross-Modal Representations","display_name":"Unsupervised Improvement of Audio-Text Cross-Modal Representations","publication_year":2023,"publication_date":"2023-10-18","ids":{"openalex":"https://openalex.org/W4387760932","doi":"https://doi.org/10.1109/waspaa58266.2023.10248180"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248180","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/waspaa58266.2023.10248180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102709539","display_name":"Zhepei Wang","orcid":"https://orcid.org/0000-0001-7845-5273"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhepei Wang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023830739","display_name":"Cem Subakan","orcid":"https://orcid.org/0000-0002-7593-6589"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Cem Subakan","raw_affiliation_strings":["Universit&#x00E9; Laval","Concordia University","Mila-Quebec AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; Laval","institution_ids":[]},{"raw_affiliation_string":"Concordia University","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"Mila-Quebec AI Institute","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042472021","display_name":"Krishna Subramani","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Subramani","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101600013","display_name":"Junkai Wu","orcid":"https://orcid.org/0000-0003-1541-0267"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junkai Wu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057729011","display_name":"Tiago Fernandes Tavares","orcid":"https://orcid.org/0000-0002-9104-613X"},"institutions":[{"id":"https://openalex.org/I52977244","display_name":"Insper","ror":"https://ror.org/02nmavx05","country_code":"BR","type":"education","lineage":["https://openalex.org/I52977244"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Tiago Tavares","raw_affiliation_strings":["Insper"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insper","institution_ids":["https://openalex.org/I52977244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009630456","display_name":"F\u00e1bio J. Ayres","orcid":"https://orcid.org/0009-0000-6821-4687"},"institutions":[{"id":"https://openalex.org/I52977244","display_name":"Insper","ror":"https://ror.org/02nmavx05","country_code":"BR","type":"education","lineage":["https://openalex.org/I52977244"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Fabio Ayres","raw_affiliation_strings":["Insper"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insper","institution_ids":["https://openalex.org/I52977244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1507732,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9916999936103821,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9830999970436096,"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":0.8307176828384399},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6299604773521423},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5919439196586609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5872504711151123},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5695781707763672},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5494562387466431},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.472455769777298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41940805315971375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8307176828384399},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6299604773521423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5919439196586609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5872504711151123},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5695781707763672},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5494562387466431},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.472455769777298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41940805315971375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/waspaa58266.2023.10248180","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/waspaa58266.2023.10248180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2593116425","https://openalex.org/W2913668833","https://openalex.org/W2963341956","https://openalex.org/W2995348821","https://openalex.org/W3015591594","https://openalex.org/W3094550259","https://openalex.org/W3126337491","https://openalex.org/W3162331882","https://openalex.org/W3176445421","https://openalex.org/W3206996142","https://openalex.org/W3215626407","https://openalex.org/W4205689591","https://openalex.org/W4226109839","https://openalex.org/W4284898017","https://openalex.org/W4312626422","https://openalex.org/W4312923322","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4393158799","https://openalex.org/W6747331233","https://openalex.org/W6774314701","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6803872405","https://openalex.org/W6869415701"],"related_works":["https://openalex.org/W1573992054","https://openalex.org/W1599690842","https://openalex.org/W2753053412","https://openalex.org/W2665157442","https://openalex.org/W3108840034","https://openalex.org/W4388169484","https://openalex.org/W2363259562","https://openalex.org/W3036937347","https://openalex.org/W3149224203","https://openalex.org/W2914339338"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,31,102,116],"using":[3],"language":[4],"models":[5],"to":[6,28,61,81,88,112],"obtain":[7,113],"cross-modal":[8],"audio-text":[9,52,83],"representations":[10,45,68],"have":[11],"overcome":[12],"the":[13,26,63,91],"limitations":[14],"of":[15,50,66,118],"conventional":[16],"training":[17],"approaches":[18,60],"that":[19,85,96],"use":[20,87],"predefined":[21],"labels.":[22],"This":[23],"has":[24],"allowed":[25],"community":[27],"make":[29],"progress":[30],"tasks":[32],"like":[33],"zero-shot":[34,119],"classification,":[35],"which":[36],"would":[37],"otherwise":[38],"not":[39],"be":[40],"possible.":[41],"However,":[42],"learning":[43,64],"such":[44,67],"requires":[46],"a":[47,105],"large":[48],"amount":[49],"human-annotated":[51],"pairs.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,86,109],"study":[58],"unsupervised":[59],"improve":[62,90],"framework":[65],"with":[69,104],"unpaired":[70],"text":[71],"and":[72,77],"audio.":[73],"We":[74,93],"explore":[75],"domain-unspecific":[76],"domain-specific":[78,98],"curation":[79,99],"methods":[80],"create":[82],"pairs":[84],"further":[89],"model.":[92],"also":[94],"show":[95],"when":[97],"is":[100],"used":[101],"conjunction":[103],"soft-labeled":[106],"contrastive":[107],"loss,":[108],"are":[110],"able":[111],"significant":[114],"improvement":[115],"terms":[117],"classification":[120,126,130],"performance":[121],"on":[122],"downstream":[123],"sound":[124],"event":[125],"or":[127],"acoustic":[128],"scene":[129],"tasks.":[131]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
