{"id":"https://openalex.org/W4224916701","doi":"https://doi.org/10.1109/icassp43922.2022.9747594","title":"RawNeXt: Speaker Verification System For Variable-Duration Utterances With Deep Layer Aggregation And Extended Dynamic Scaling Policies","display_name":"RawNeXt: Speaker Verification System For Variable-Duration Utterances With Deep Layer Aggregation And Extended Dynamic Scaling Policies","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224916701","doi":"https://doi.org/10.1109/icassp43922.2022.9747594"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747594","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5101866564","display_name":"Ju-ho Kim","orcid":"https://orcid.org/0009-0001-4055-4564"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Ju-Ho Kim","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103211980","display_name":"Hye-jin Shim","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hye-Jin Shim","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046942516","display_name":"Jungwoo Heo","orcid":"https://orcid.org/0009-0008-7977-2789"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jungwoo Heo","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030475312","display_name":"Ha-Jin Yu","orcid":"https://orcid.org/0000-0003-3657-0665"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ha-Jin Yu","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101866564"],"corresponding_institution_ids":["https://openalex.org/I124633538"],"apc_list":null,"apc_paid":null,"fwci":1.6631,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85644258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7647","last_page":"7651"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9922000169754028,"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/T11309","display_name":"Music and Audio Processing","score":0.9915000200271606,"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":0.840201735496521},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6740437746047974},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6077836751937866},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6029975414276123},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5072981715202332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4764281213283539},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4587221145629883},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.452291876077652},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.44939807057380676},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.44015058875083923},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43450862169265747},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4314056932926178},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4277118444442749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3667682409286499},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33736473321914673},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32686689496040344},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.21421250700950623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.840201735496521},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6740437746047974},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6077836751937866},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6029975414276123},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5072981715202332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4764281213283539},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4587221145629883},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.452291876077652},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.44939807057380676},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.44015058875083923},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43450862169265747},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4314056932926178},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4277118444442749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3667682409286499},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33736473321914673},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32686689496040344},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.21421250700950623},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic 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/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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747594","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2150769028","https://openalex.org/W2219249508","https://openalex.org/W2549139847","https://openalex.org/W2565639579","https://openalex.org/W2747238065","https://openalex.org/W2785523195","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2916301830","https://openalex.org/W2949391068","https://openalex.org/W2963323244","https://openalex.org/W2964052309","https://openalex.org/W2969985801","https://openalex.org/W2972441390","https://openalex.org/W2972627751","https://openalex.org/W2981087920","https://openalex.org/W3008104819","https://openalex.org/W3013020904","https://openalex.org/W3020953549","https://openalex.org/W3094374485","https://openalex.org/W3095201711","https://openalex.org/W3096084197","https://openalex.org/W3096235116","https://openalex.org/W3096792157","https://openalex.org/W3111481301","https://openalex.org/W3112165001","https://openalex.org/W3142516134","https://openalex.org/W3149926570","https://openalex.org/W4286981691","https://openalex.org/W6688816777","https://openalex.org/W6784400926","https://openalex.org/W6784784087","https://openalex.org/W6786547643","https://openalex.org/W6787439801"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2580934630","https://openalex.org/W2038117447","https://openalex.org/W112947718","https://openalex.org/W1998549096","https://openalex.org/W2803679320"],"abstract_inverted_index":{"Despite":[0],"achieving":[1],"satisfactory":[2],"performance":[3,142],"in":[4,100,116],"speaker":[5,30,57,113],"verification":[6,31],"using":[7],"deep":[8,52],"neural":[9],"networks,":[10],"variable-duration":[11],"utterances":[12,136],"remain":[13],"a":[14,29],"challenge":[15],"that":[16,35,138],"threatens":[17],"the":[18,46,86,89,94,128,145],"robustness":[19],"of":[20,41,65,88,96,133],"systems.":[21,148],"To":[22],"deal":[23],"with":[24],"this":[25],"issue,":[26],"we":[27],"propose":[28],"system":[32],"called":[33],"RawNeXt":[34,139],"can":[36,111],"handle":[37],"input":[38],"raw":[39],"waveforms":[40],"arbitrary":[42],"length":[43,87,123],"by":[44,59,91],"employing":[45],"following":[47],"two":[48,106],"components:":[49],"(1)":[50],"A":[51],"layer":[53],"aggregation":[54],"strategy":[55],"enhances":[56],"information":[58,118],"iteratively":[60],"and":[61,69,119,151],"hierarchically":[62],"aggregating":[63],"features":[64,83],"various":[66,134],"time":[67],"scales":[68],"spectral":[70],"channels":[71],"output":[72],"from":[73],"blocks.":[74],"(2)":[75],"An":[76],"extended":[77],"dynamic":[78],"scaling":[79],"policy":[80],"flexibly":[81],"processes":[82],"according":[84],"to":[85,104,144],"utterance":[90],"selectively":[92],"merging":[93],"activations":[95],"different":[97],"resolution":[98],"branches":[99],"each":[101],"block.":[102],"Owing":[103],"these":[105],"components,":[107],"our":[108],"proposed":[109,147],"model":[110,153],"extract":[112],"embeddings":[114],"rich":[115],"time-spectral":[117],"operate":[120],"dynamically":[121],"on":[122,127],"variations.":[124],"Experimental":[125],"results":[126],"VoxCeleb1":[129],"test":[130],"set":[131],"consisting":[132],"duration":[135],"demonstrate":[137],"achieves":[140],"state-of-the-art":[141],"compared":[143],"recently":[146],"Our":[149],"code":[150],"trained":[152],"weights":[154],"are":[155],"available":[156],"at":[157],"https://github.com/wngh1187/RawNeXt.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}