{"id":"https://openalex.org/W3158978276","doi":"https://doi.org/10.21437/interspeech.2021-2227","title":"Audio Retrieval with Natural Language Queries","display_name":"Audio Retrieval with Natural Language Queries","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3158978276","doi":"https://doi.org/10.21437/interspeech.2021-2227","mag":"3158978276"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-2227","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.02192","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036345396","display_name":"Andreea-Maria Oncescu","orcid":"https://orcid.org/0000-0001-9730-3873"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andreea-Maria Oncescu","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001366802","display_name":"A. Sophia Koepke","orcid":"https://orcid.org/0000-0002-5807-0576"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"A. Sophia Koepke","raw_affiliation_strings":["University of T\u00fcbingen, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"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/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o F. Henriques","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"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/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zeynep Akata","raw_affiliation_strings":["University of T\u00fcbingen, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"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/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Samuel Albanie","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3624,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.47935368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2411","last_page":"2415"},"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":0.9968000054359436,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8754512071609497},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6684660911560059},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.625092625617981},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5955458283424377},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5570886731147766},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4806972146034241},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4472110867500305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3610047698020935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8754512071609497},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6684660911560059},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.625092625617981},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5955458283424377},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5570886731147766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4806972146034241},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4472110867500305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3610047698020935},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2021-2227","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.02192","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.02192","pdf_url":"https://arxiv.org/pdf/2105.02192","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":"","raw_type":"text"},{"id":"mag:3158978276","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2105.02192.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:ora.ox.ac.uk:uuid:cc107781-c321-459d-ba0b-70cef6c52222","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:cc107781-c321-459d-ba0b-70cef6c52222","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"Conference item"},{"id":"doi:10.48550/arxiv.2105.02192","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.02192","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.02192","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.02192","pdf_url":"https://arxiv.org/pdf/2105.02192","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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8600000143051147}],"awards":[{"id":"https://openalex.org/G1562512020","display_name":null,"funder_award_id":"206/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"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/G5003611146","display_name":"Visual AI: An Open World Interpretable Visual Transformer","funder_award_id":"EP/T028572/1","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/G7907426250","display_name":"EXC 2064: Maschinelles Lernen: Neue Perspektiven f\u00fcr die Wissenschaft","funder_award_id":"390727645","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"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"},{"id":"https://openalex.org/G8556661049","display_name":null,"funder_award_id":"390727645","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/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":62,"referenced_works":["https://openalex.org/W877909479","https://openalex.org/W1600745603","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/W2123301721","https://openalex.org/W2149557440","https://openalex.org/W2154016477","https://openalex.org/W2176625348","https://openalex.org/W2179042386","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/W2623327532","https://openalex.org/W2732026016","https://openalex.org/W2775505379","https://openalex.org/W2783973932","https://openalex.org/W2791956393","https://openalex.org/W2796207103","https://openalex.org/W2808399042","https://openalex.org/W2916103538","https://openalex.org/W2940092410","https://openalex.org/W2945761034","https://openalex.org/W2948982921","https://openalex.org/W2950577311","https://openalex.org/W2963022469","https://openalex.org/W2963155035","https://openalex.org/W2963446712","https://openalex.org/W2963703197","https://openalex.org/W2963916161","https://openalex.org/W2964213897","https://openalex.org/W2964287480","https://openalex.org/W2964891022","https://openalex.org/W2968848930","https://openalex.org/W2970803838","https://openalex.org/W2972073579","https://openalex.org/W2973109987","https://openalex.org/W2980037812","https://openalex.org/W2994689640","https://openalex.org/W3015371781","https://openalex.org/W3015591594","https://openalex.org/W3023441976","https://openalex.org/W3043840704","https://openalex.org/W3092867190","https://openalex.org/W3094550259","https://openalex.org/W3112467147","https://openalex.org/W3122335742","https://openalex.org/W3132747082","https://openalex.org/W3161945002","https://openalex.org/W3208082774"],"related_works":["https://openalex.org/W3198452188","https://openalex.org/W2072938301","https://openalex.org/W2539610515","https://openalex.org/W1576578512","https://openalex.org/W2765345004","https://openalex.org/W2970944013","https://openalex.org/W2129854314","https://openalex.org/W2965458216","https://openalex.org/W2765272479","https://openalex.org/W3035309251","https://openalex.org/W3103534990","https://openalex.org/W2012474104","https://openalex.org/W1978183412","https://openalex.org/W1982795953","https://openalex.org/W2097241500","https://openalex.org/W2981785383","https://openalex.org/W3013937728","https://openalex.org/W3042208375","https://openalex.org/W3175939205","https://openalex.org/W2047583882"],"abstract_inverted_index":{"We":[0,44,67],"consider":[1],"the":[2,22,39,59],"task":[3],"of":[4,61],"retrieving":[5],"audio":[6,32,54,65,79],"using":[7,34],"free-form":[8,82],"natural":[9],"language":[10],"queries.":[11,84],"To":[12],"study":[13],"this":[14],"problem,":[15],"which":[16],"has":[17],"received":[18],"limited":[19],"attention":[20],"in":[21],"existing":[23],"literature,":[24],"we":[25,57],"introduce":[26],"challenging":[27],"new":[28],"benchmarks":[29,48,71],"for":[30,52],"text-based":[31,78],"retrieval":[33,80],"text":[35,83],"annotations":[36],"sourced":[37],"from":[38],"Audiocaps":[40],"and":[41],"Clotho":[42],"datasets.":[43],"then":[45],"employ":[46],"these":[47],"to":[49],"establish":[50],"baselines":[51],"cross-modal":[53,77],"retrieval,":[55],"where":[56],"demonstrate":[58],"benefits":[60],"pre-training":[62],"on":[63],"diverse":[64],"tasks.":[66],"hope":[68],"that":[69],"our":[70],"will":[72],"inspire":[73],"further":[74],"research":[75],"into":[76],"with":[81]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}