{"id":"https://openalex.org/W2916104401","doi":"https://doi.org/10.1109/icassp.2019.8683120","title":"Utterance-level Aggregation for Speaker Recognition in the Wild","display_name":"Utterance-level Aggregation for Speaker Recognition in the Wild","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2916104401","doi":"https://doi.org/10.1109/icassp.2019.8683120","mag":"2916104401"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5076097168","display_name":"Weidi Xie","orcid":"https://orcid.org/0000-0003-3804-2639"},"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"]},{"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":true,"raw_author_name":"Weidi Xie","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, UK","institution_ids":["https://openalex.org/I2802123492","https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036002448","display_name":"Arsha Nagrani","orcid":"https://orcid.org/0000-0003-2190-9013"},"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"]},{"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":"Arsha Nagrani","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, UK","institution_ids":["https://openalex.org/I2802123492","https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"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"]},{"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":"Joon Son Chung","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, UK","institution_ids":["https://openalex.org/I2802123492","https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573"},"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"]},{"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":"Andrew Zisserman","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, UK","institution_ids":["https://openalex.org/I2802123492","https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076097168"],"corresponding_institution_ids":["https://openalex.org/I2802123492","https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":31.2135,"has_fulltext":false,"cited_by_count":325,"citation_normalized_percentile":{"value":0.99741764,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5791","last_page":"5795"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7797409296035767},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6876384019851685},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6810743808746338},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6554915308952332},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5941442847251892},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5911588668823242},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5395729541778564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5292377471923828},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5287415981292725},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5144141316413879},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.497910737991333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4811031222343445},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.41111502051353455},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1600503921508789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797409296035767},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6876384019851685},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6810743808746338},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6554915308952332},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5941442847251892},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5911588668823242},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5395729541778564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5292377471923828},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5287415981292725},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5144141316413879},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.497910737991333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4811031222343445},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.41111502051353455},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1600503921508789},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8683120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:7ab74cff-6c8d-4fdd-b024-4bd297a37e8d","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:7ab74cff-6c8d-4fdd-b024-4bd297a37e8d","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":"","raw_type":"Conference item"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1277543710","display_name":null,"funder_award_id":"EP/M013774/1","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1963882359","https://openalex.org/W2010062708","https://openalex.org/W2056119007","https://openalex.org/W2179042386","https://openalex.org/W2271840356","https://openalex.org/W2516764878","https://openalex.org/W2549349626","https://openalex.org/W2612434969","https://openalex.org/W2620629206","https://openalex.org/W2726515241","https://openalex.org/W2746742816","https://openalex.org/W2748488820","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2884412522","https://openalex.org/W2890704021","https://openalex.org/W2890964092","https://openalex.org/W2899771611","https://openalex.org/W2962788625","https://openalex.org/W2962959915","https://openalex.org/W2963077989","https://openalex.org/W2963371159","https://openalex.org/W2963507712","https://openalex.org/W2964216323","https://openalex.org/W3103152812","https://openalex.org/W4248480789","https://openalex.org/W4289750118","https://openalex.org/W6694517276","https://openalex.org/W6737575990","https://openalex.org/W6745983287","https://openalex.org/W6753575415","https://openalex.org/W6754615656","https://openalex.org/W6755154125","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2562096895","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2351687372","https://openalex.org/W2383414243","https://openalex.org/W2464407842","https://openalex.org/W2914064142"],"abstract_inverted_index":{"The":[0],"objective":[1],"of":[2,16,29,38,46,86,114],"this":[3,33],"paper":[4],"is":[5,130],"speaker":[6,53,100],"recognition":[7,54],"`in":[8,123],"the":[9,27,36,44,87,95,112,124],"wild'":[10,125],"-":[11],"where":[12],"utterances":[13],"may":[14],"be":[15,76],"variable":[17],"length":[18,116,129],"and":[19,43,62,119],"also":[20,110],"contain":[21],"irrelevant":[22],"signals.":[23],"Crucial":[24],"elements":[25],"in":[26],"design":[28],"deep":[30,55],"networks":[31],"for":[32,99,122],"task":[34],"are":[35],"type":[37],"trunk":[39,60],"(frame":[40],"level)":[41],"network,":[42,56],"method":[45],"temporal":[47],"aggregation.":[48],"We":[49,79,109],"propose":[50],"a":[51,58,63,91,127],"powerful":[52],"using":[57],"`thin-ResNet'":[59],"architecture,":[61],"dictionary-based":[64],"NetVLAD":[65],"or":[66],"GhostVLAD":[67],"layer":[68],"to":[69],"aggregate":[70],"features":[71],"across":[72],"time,":[73],"that":[74,81,121],"can":[75],"trained":[77],"end-to-end.":[78],"show":[80],"our":[82],"network":[83],"achieves":[84],"state":[85],"art":[88],"performance":[89],"by":[90],"significant":[92],"margin":[93],"on":[94,117],"VoxCeleb1":[96],"test":[97],"set":[98],"recognition,":[101],"whilst":[102],"requiring":[103],"fewer":[104],"parameters":[105],"than":[106],"previous":[107],"methods.":[108],"investigate":[111],"effect":[113],"utterance":[115],"performance,":[118],"conclude":[120],"data,":[126],"longer":[128],"beneficial.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":51},{"year":2022,"cited_by_count":53},{"year":2021,"cited_by_count":73},{"year":2020,"cited_by_count":70},{"year":2019,"cited_by_count":19}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}