{"id":"https://openalex.org/W4221157007","doi":"https://doi.org/10.21437/interspeech.2022-11115","title":"On Metric Learning for Audio-Text Cross-Modal Retrieval","display_name":"On Metric Learning for Audio-Text Cross-Modal Retrieval","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221157007","doi":"https://doi.org/10.21437/interspeech.2022-11115"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11115","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11115","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5070892237","display_name":"Xinhao Mei","orcid":"https://orcid.org/0000-0001-6079-5130"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xinhao Mei","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"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/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101153327","display_name":"Jianyuan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianyuan Sun","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"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/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Plumbley","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"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/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4142","last_page":"4146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9805999994277954,"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":0.9718999862670898,"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":0.7831871509552002},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7344937324523926},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6716777682304382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45604777336120605},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41279157996177673},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39868879318237305},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34417346119880676},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0590948760509491}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831871509552002},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7344937324523926},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6716777682304382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45604777336120605},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41279157996177673},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39868879318237305},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34417346119880676},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0590948760509491},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-11115","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11115","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11163120890002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[{"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/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2010486494","https://openalex.org/W2156387975","https://openalex.org/W2593116425","https://openalex.org/W2774267535","https://openalex.org/W2796207103","https://openalex.org/W2896457183","https://openalex.org/W2940092410","https://openalex.org/W2965458216","https://openalex.org/W2988823324","https://openalex.org/W3005680577","https://openalex.org/W3013020904","https://openalex.org/W3015591594","https://openalex.org/W3035212740","https://openalex.org/W3043840704","https://openalex.org/W3091588028","https://openalex.org/W3094550259","https://openalex.org/W3099206234","https://openalex.org/W3109684201","https://openalex.org/W3185739472","https://openalex.org/W3186781156","https://openalex.org/W3189036352","https://openalex.org/W4210913346","https://openalex.org/W4226211003","https://openalex.org/W4303578640","https://openalex.org/W4312898271"],"related_works":["https://openalex.org/W2357241418","https://openalex.org/W2789919619","https://openalex.org/W2086064646","https://openalex.org/W2119135658","https://openalex.org/W2115485936","https://openalex.org/W2293457016","https://openalex.org/W3022131925","https://openalex.org/W3169305685","https://openalex.org/W2792377126","https://openalex.org/W2349174110"],"abstract_inverted_index":{"Audio-text":[0],"retrieval":[1,24,52,87,96,118],"aims":[2],"at":[3,161],"retrieving":[4],"a":[5,12,17],"target":[6],"audio":[7],"clip":[8],"or":[9],"caption":[10],"from":[11,140],"pool":[13],"of":[14,63,110,124],"candidates":[15],"given":[16],"query":[18],"in":[19],"another":[20],"modality.Solving":[21],"such":[22,89],"cross-modal":[23,51,86],"task":[25],"is":[26,97,159],"challenging":[27],"because":[28],"it":[29],"not":[30],"only":[31],"requires":[32,42],"learning":[33,59,113,127,142],"robust":[34],"feature":[35],"representations":[36],"for":[37],"both":[38,62],"modalities,":[39],"but":[40],"also":[41],"capturing":[43],"the":[44,108,116,130,154],"fine-grained":[45],"alignment":[46],"between":[47],"these":[48],"two":[49],"modalities.Existing":[50],"models":[53],"are":[54,76,82],"mostly":[55],"optimized":[56],"by":[57],"metric":[58,112,126],"objectives":[60,114,128],"as":[61,90],"them":[64],"attempt":[65],"to":[66,69,106],"map":[67],"data":[68,75,81],"an":[70,99,121],"embedding":[71],"space,":[72],"where":[73],"similar":[74],"close":[77],"together":[78],"and":[79,92,132,149,152],"dissimilar":[80],"far":[83],"apart.Unlike":[84],"other":[85],"tasks":[88],"image-text":[91],"video-text":[93],"retrievals,":[94],"audio-text":[95,117],"still":[98],"unexplored":[100],"task.In":[101],"this":[102],"work,":[103],"we":[104],"aim":[105],"study":[107],"impact":[109],"different":[111,147],"on":[115,129],"task.We":[119],"present":[120],"extensive":[122],"evaluation":[123],"popular":[125,155],"AudioCaps":[131],"Clotho":[133],"datasets.We":[134],"demonstrate":[135],"that":[136],"NT-Xent":[137],"loss":[138],"adapted":[139],"self-supervised":[141],"shows":[143],"stable":[144],"performance":[145],"across":[146],"datasets":[148],"training":[150],"settings,":[151],"outperforms":[153],"triplet-based":[156],"losses.Our":[157],"code":[158],"available":[160],"https://github.com/XinhaoMei/audio-text_retrieval.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}