{"id":"https://openalex.org/W4210913346","doi":"https://doi.org/10.1109/tmm.2022.3149712","title":"Audio Retrieval With Natural Language Queries: A Benchmark Study","display_name":"Audio Retrieval With Natural Language Queries: A Benchmark Study","publication_year":2022,"publication_date":"2022-02-08","ids":{"openalex":"https://openalex.org/W4210913346","doi":"https://doi.org/10.1109/tmm.2022.3149712"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3149712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3149712","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2112.09418","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001366802","display_name":"A. Sophia Koepke","orcid":"https://orcid.org/0000-0002-5807-0576"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"A. Sophia Koepke","raw_affiliation_strings":["Explainable Machine Learning Group at the University of Tübingen, Tübingen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5807-0576","affiliations":[{"raw_affiliation_string":"Explainable Machine Learning Group at the University of Tübingen, Tübingen, Germany","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036345396","display_name":"Andreea-Maria Oncescu","orcid":"https://orcid.org/0000-0001-9730-3873"},"institutions":[{"id":"https://openalex.org/I2802123492","display_name":"Oxford Research Group","ror":"https://ror.org/00z4w4f29","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802123492"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andreea-Maria Oncescu","raw_affiliation_strings":["Visual Geometry Group at the University of Oxford, Oxford, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group at the University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I2802123492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109730096","display_name":"Jo\u00e3o F. Henriques","orcid":"https://orcid.org/0000-0002-2478-2102"},"institutions":[{"id":"https://openalex.org/I2802123492","display_name":"Oxford Research Group","ror":"https://ror.org/00z4w4f29","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802123492"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o F. Henriques","raw_affiliation_strings":["Visual Geometry Group at the University of Oxford, Oxford, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group at the University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I2802123492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040372929","display_name":"Zeynep Akata","orcid":"https://orcid.org/0000-0002-1432-7747"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zeynep Akata","raw_affiliation_strings":["Explainable Machine Learning Group at the University of Tübingen, Tübingen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1432-7747","affiliations":[{"raw_affiliation_string":"Explainable Machine Learning Group at the University of Tübingen, Tübingen, Germany","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102018867","display_name":"Samuel Albanie","orcid":"https://orcid.org/0000-0003-1732-9198"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Samuel Albanie","raw_affiliation_strings":["Department of Engineering at the University of Cambridge, Cambridge, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1732-9198","affiliations":[{"raw_affiliation_string":"Department of Engineering at the University of Cambridge, Cambridge, U.K","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.0054,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.98656716,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"2675","last_page":"2685"},"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":0.9987999796867371,"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":0.9926999807357788,"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":0.9051676988601685},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6098051071166992},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.587043821811676},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5580360293388367},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5310025215148926},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.46790868043899536},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45533838868141174},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4350598454475403},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33639705181121826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.327215313911438},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.21958434581756592},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1424461007118225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9051676988601685},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6098051071166992},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.587043821811676},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5580360293388367},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5310025215148926},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.46790868043899536},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45533838868141174},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4350598454475403},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33639705181121826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.327215313911438},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.21958434581756592},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1424461007118225},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2022.3149712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3149712","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2112.09418","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.09418","pdf_url":"https://arxiv.org/pdf/2112.09418","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2112.09418","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.09418","pdf_url":"https://arxiv.org/pdf/2112.09418","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[{"id":"https://openalex.org/G3391221791","display_name":null,"funder_award_id":"EP/T028572/1 Visual AI","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G724330786","display_name":null,"funder_award_id":"2285346","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8060345762","display_name":null,"funder_award_id":"RF\\201819\\18\\163","funder_id":"https://openalex.org/F4320320005","funder_display_name":"Royal Academy of Engineering"},{"id":"https://openalex.org/G8161891803","display_name":null,"funder_award_id":"EP/T028572/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"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":107,"referenced_works":["https://openalex.org/W877909479","https://openalex.org/W1600745603","https://openalex.org/W1614298861","https://openalex.org/W2010486494","https://openalex.org/W2033875152","https://openalex.org/W2046955072","https://openalex.org/W2048174296","https://openalex.org/W2052666245","https://openalex.org/W2074188409","https://openalex.org/W2086384421","https://openalex.org/W2101305062","https://openalex.org/W2103279261","https://openalex.org/W2108598243","https://openalex.org/W2111331420","https://openalex.org/W2112861900","https://openalex.org/W2123301721","https://openalex.org/W2139501017","https://openalex.org/W2142524229","https://openalex.org/W2149557440","https://openalex.org/W2176625348","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2524365899","https://openalex.org/W2526050071","https://openalex.org/W2558358930","https://openalex.org/W2593116425","https://openalex.org/W2622886161","https://openalex.org/W2732026016","https://openalex.org/W2739107216","https://openalex.org/W2753311918","https://openalex.org/W2775505379","https://openalex.org/W2791956393","https://openalex.org/W2796207103","https://openalex.org/W2808399042","https://openalex.org/W2889650715","https://openalex.org/W2896457183","https://openalex.org/W2916103538","https://openalex.org/W2940092410","https://openalex.org/W2951019013","https://openalex.org/W2962968152","https://openalex.org/W2963022469","https://openalex.org/W2963155035","https://openalex.org/W2963446712","https://openalex.org/W2963507712","https://openalex.org/W2963703197","https://openalex.org/W2963801643","https://openalex.org/W2963902314","https://openalex.org/W2963916161","https://openalex.org/W2964153283","https://openalex.org/W2964213897","https://openalex.org/W2964287480","https://openalex.org/W2964891022","https://openalex.org/W2965458216","https://openalex.org/W2968917279","https://openalex.org/W2972073579","https://openalex.org/W2973109987","https://openalex.org/W2980037812","https://openalex.org/W2982343573","https://openalex.org/W3015371781","https://openalex.org/W3015591594","https://openalex.org/W3041053424","https://openalex.org/W3043840704","https://openalex.org/W3094550259","https://openalex.org/W3095941556","https://openalex.org/W3102887392","https://openalex.org/W3112467147","https://openalex.org/W3122335742","https://openalex.org/W3123416659","https://openalex.org/W3133481345","https://openalex.org/W3146463283","https://openalex.org/W3152798676","https://openalex.org/W3153005511","https://openalex.org/W3160577380","https://openalex.org/W3161753238","https://openalex.org/W3161945002","https://openalex.org/W3163843406","https://openalex.org/W3177365819","https://openalex.org/W3185739472","https://openalex.org/W3186781156","https://openalex.org/W3198452188","https://openalex.org/W3204588463","https://openalex.org/W4294576248","https://openalex.org/W4297690166","https://openalex.org/W6636510571","https://openalex.org/W6678262379","https://openalex.org/W6681067464","https://openalex.org/W6682395106","https://openalex.org/W6687483927","https://openalex.org/W6730383699","https://openalex.org/W6738806211","https://openalex.org/W6739020500","https://openalex.org/W6747331233","https://openalex.org/W6748069790","https://openalex.org/W6749158954","https://openalex.org/W6750041603","https://openalex.org/W6755207826","https://openalex.org/W6766196973","https://openalex.org/W6766582784","https://openalex.org/W6767164110","https://openalex.org/W6780924892","https://openalex.org/W6784824658","https://openalex.org/W6787564935","https://openalex.org/W6793759846","https://openalex.org/W6797746672","https://openalex.org/W6798955355","https://openalex.org/W6799303324"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W3009270862"],"abstract_inverted_index":{"The":[0],"objectives":[1],"of":[2,23,54,66,104,115,143],"this":[3],"work":[4],"arecross-modal":[5],"text-audio":[6,67,89,134],"and":[7,32,68,90,107,135],"audio-text":[8,69,91,136],"retrieval,":[9,70,137],"in":[10,76],"which":[11,71,102],"the":[12,17,55,64,77,141],"goal":[13],"is":[14],"to":[15,39,60,120,129],"retrieve":[16],"audio":[18,106,147,159],"content":[19],"from":[20,94],"a":[21,28,112],"pool":[22],"candidates":[24],"that":[25,117,151],"best":[26],"matches":[27],"given":[29],"written":[30],"description":[31],"vice":[33],"versa.":[34],"Text-audio":[35],"retrieval":[36,92,160],"enables":[37],"users":[38],"search":[40],"large":[41],"databases":[42],"through":[43],"an":[44],"intuitive":[45],"interface:":[46],"they":[47,57],"simply":[48],"issue":[49],"free-form":[50,162],"natural":[51,108],"language":[52,109],"descriptions":[53,110],"sound":[56],"would":[58],"like":[59],"hear.":[61],"To":[62],"study":[63],"tasks":[65],"have":[72],"received":[73],"limited":[74],"attention":[75],"existing":[78],"literature,":[79],"we":[80,99,139],"introduce":[81,100],"three":[82,127],"challenging":[83],"new":[84],"benchmarks.":[85],"We":[86,124,149],"first":[87],"construct":[88],"benchmarks":[93,128,153],"theAudioCapsandClothoaudio":[95],"captioning":[96],"datasets.":[97],"Additionally,":[98],"theSoundDescsbenchmark,":[101],"consists":[103],"paired":[105],"for":[111,132],"diverse":[113,146],"collection":[114],"sounds":[116],"are":[118],"complementary":[119],"those":[121],"found":[122],"inAudioCapsandClotho.":[123],"employ":[125],"these":[126],"establish":[130],"baselines":[131],"cross-modal":[133],"where":[138],"demonstrate":[140],"benefits":[142],"pre-training":[144],"on":[145],"tasks.":[148],"hope":[150],"our":[152],"will":[154],"inspire":[155],"further":[156],"research":[157],"into":[158],"with":[161],"text":[163],"queries.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}