{"id":"https://openalex.org/W4372338181","doi":"https://doi.org/10.1109/icassp49357.2023.10096839","title":"Short-Segment Speaker Verification Using ECAPA-TDNN with Multi-Resolution Encoder","display_name":"Short-Segment Speaker Verification Using ECAPA-TDNN with Multi-Resolution Encoder","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372338181","doi":"https://doi.org/10.1109/icassp49357.2023.10096839"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5038258742","display_name":"Sang-Wook Han","orcid":"https://orcid.org/0000-0002-4098-3326"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sangwook Han","raw_affiliation_strings":["Gwangju Institute of Science and Technology,School of Electrical Engineering and Computer Science,Gwangju,Korea","School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"Gwangju Institute of Science and Technology,School of Electrical Engineering and Computer Science,Gwangju,Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004566479","display_name":"Youngdo Ahn","orcid":"https://orcid.org/0000-0001-7579-662X"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngdo Ahn","raw_affiliation_strings":["Gwangju Institute of Science and Technology,School of Electrical Engineering and Computer Science,Gwangju,Korea","School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"Gwangju Institute of Science and Technology,School of Electrical Engineering and Computer Science,Gwangju,Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016956493","display_name":"Kyeongmuk Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyeongmuk Kang","raw_affiliation_strings":["Gwangju Institute of Science and Technology,School of Electrical Engineering and Computer Science,Gwangju,Korea","School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"Gwangju Institute of Science and Technology,School of Electrical Engineering and Computer Science,Gwangju,Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054155133","display_name":"Jong Won Shin","orcid":"https://orcid.org/0000-0002-8910-0264"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong Won Shin","raw_affiliation_strings":["Gwangju Institute of Science and Technology,School of Electrical Engineering and Computer Science,Gwangju,Korea","School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"Gwangju Institute of Science and Technology,School of Electrical Engineering and Computer Science,Gwangju,Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea","institution_ids":["https://openalex.org/I39534123"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038258742"],"corresponding_institution_ids":["https://openalex.org/I39534123"],"apc_list":null,"apc_paid":null,"fwci":2.5579,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91362033,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9955999851226807,"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":0.8294700384140015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6361454129219055},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5819669961929321},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.537621796131134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4963687062263489},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47655776143074036},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.46275684237480164},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44041168689727783},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43868255615234375},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.42591792345046997},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2557656764984131},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.1172962486743927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8294700384140015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6361454129219055},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5819669961929321},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.537621796131134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4963687062263489},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47655776143074036},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.46275684237480164},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44041168689727783},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43868255615234375},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.42591792345046997},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2557656764984131},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.1172962486743927},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2114925438","https://openalex.org/W2219249508","https://openalex.org/W2752782242","https://openalex.org/W2797583228","https://openalex.org/W2808631503","https://openalex.org/W2928165649","https://openalex.org/W2952218014","https://openalex.org/W2969985801","https://openalex.org/W2972627751","https://openalex.org/W3020953549","https://openalex.org/W3024869864","https://openalex.org/W3088315586","https://openalex.org/W3094897602","https://openalex.org/W3096084197","https://openalex.org/W3096792157","https://openalex.org/W3099330747","https://openalex.org/W3149926570","https://openalex.org/W3162520476","https://openalex.org/W3197940657","https://openalex.org/W3206189675","https://openalex.org/W4210631835","https://openalex.org/W4224916701","https://openalex.org/W4225635674","https://openalex.org/W4297841773","https://openalex.org/W6688816777","https://openalex.org/W6750665317","https://openalex.org/W6780226713","https://openalex.org/W6786547643"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2021595906","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W2766087987","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W2095992409","https://openalex.org/W2186375278"],"abstract_inverted_index":{"Time-domain":[0],"approaches":[1,16,118],"have":[2],"shown":[3],"the":[4,8,22,39,52,62,80,100,104,111,120,129,140],"potential":[5],"to":[6,74,90],"improve":[7],"performance":[9,138],"of":[10],"speaker":[11,82],"verification,":[12],"but":[13],"still":[14],"predominant":[15],"utilize":[17],"hand-crafted":[18],"features":[19,28,93,102],"such":[20],"as":[21],"mel":[23],"filterbank":[24],"energies.":[25],"Although":[26],"these":[27],"are":[29],"based":[30],"on":[31,139],"speech":[32],"perception":[33],"models":[34],"and":[35,48,55,65,98],"exhibited":[36],"impressive":[37],"performances,":[38],"fixed":[40],"frame":[41],"size":[42],"does":[43],"not":[44],"allow":[45],"good":[46],"temporal":[47,96],"spectral":[49],"resolutions":[50],"at":[51],"same":[53],"time":[54],"there":[56],"is":[57],"information":[58,78],"loss":[59],"when":[60,119],"taking":[61],"magnitude":[63],"spectrum":[64],"during":[66],"frequency":[67],"rescaling.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"propose":[73],"incorporate":[75],"multi-resolution":[76,88],"time-domain":[77],"into":[79],"ECAPA-TDNN":[81],"verification":[83],"system.":[84],"We":[85],"construct":[86],"a":[87],"encoder":[89],"extract":[91],"multiple":[92],"in":[94],"different":[95],"resolutions,":[97],"let":[99],"extracted":[101],"drive":[103],"adapter":[105],"modules.":[106],"Experimental":[107],"results":[108],"showed":[109,136],"that":[110],"proposed":[112,117,133],"method":[113],"outperformed":[114],"other":[115],"recently":[116],"input":[121],"length":[122],"was":[123],"2":[124],"seconds":[125],"or":[126],"shorter":[127],"for":[128],"VoxCeleb":[130],"dataset.":[131],"The":[132],"approach":[134],"also":[135],"superior":[137],"Google":[141],"Speech":[142],"Commands":[143],"dataset":[144],"v2.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}