{"id":"https://openalex.org/W4392909885","doi":"https://doi.org/10.1109/icassp48485.2024.10446375","title":"Diff-SV: A Unified Hierarchical Framework for Noise-Robust Speaker Verification Using Score-Based Diffusion Probabilistic Models","display_name":"Diff-SV: A Unified Hierarchical Framework for Noise-Robust Speaker Verification Using Score-Based Diffusion Probabilistic Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909885","doi":"https://doi.org/10.1109/icassp48485.2024.10446375"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/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":"middle","author":{"id":"https://openalex.org/A5101319299","display_name":"Hyun-Seo Shin","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":"Hyun-Seo Shin","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/A5113145371","display_name":"Chan-Yeong Lim","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":"Chan-Yeong Lim","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":5,"corresponding_author_ids":["https://openalex.org/A5101866564"],"corresponding_institution_ids":["https://openalex.org/I124633538"],"apc_list":null,"apc_paid":null,"fwci":1.6724,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85503582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10341","last_page":"10345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9919999837875366,"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/speaker-verification","display_name":"Speaker verification","score":0.8831847906112671},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6998304724693298},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6889591217041016},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5362958312034607},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5291351079940796},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4371494650840759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4136066734790802},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2476455569267273}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8831847906112671},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6998304724693298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6889591217041016},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5362958312034607},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5291351079940796},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4371494650840759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4136066734790802},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2476455569267273},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3268536186","display_name":null,"funder_award_id":"2023R1A2C1005744","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2159202424","https://openalex.org/W2219249508","https://openalex.org/W2407127962","https://openalex.org/W2726515241","https://openalex.org/W2802304149","https://openalex.org/W2890964092","https://openalex.org/W2963040451","https://openalex.org/W2963127163","https://openalex.org/W2969985801","https://openalex.org/W2972425344","https://openalex.org/W3005621653","https://openalex.org/W3015231328","https://openalex.org/W3024869864","https://openalex.org/W3036167779","https://openalex.org/W3160324929","https://openalex.org/W3162926177","https://openalex.org/W3196650842","https://openalex.org/W4206633762","https://openalex.org/W4221144097","https://openalex.org/W4224916701","https://openalex.org/W4239396298","https://openalex.org/W4283703262","https://openalex.org/W4372267288","https://openalex.org/W4385245566","https://openalex.org/W6679045638","https://openalex.org/W6688816777","https://openalex.org/W6747620207","https://openalex.org/W6779823529","https://openalex.org/W6781550413","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6795261426","https://openalex.org/W6795288823","https://openalex.org/W6798721538"],"related_works":["https://openalex.org/W2546089952","https://openalex.org/W2002739602","https://openalex.org/W2345647014","https://openalex.org/W2140022733","https://openalex.org/W2090976131","https://openalex.org/W1516392727","https://openalex.org/W2201192772","https://openalex.org/W3136891595","https://openalex.org/W2535030201","https://openalex.org/W1964819397"],"abstract_inverted_index":{"Background":[0],"noise":[1,99],"considerably":[2],"reduces":[3],"the":[4,38,93,102],"accuracy":[5],"and":[6,68,72,88,101],"reliability":[7],"of":[8],"speaker":[9,65,74],"verification":[10],"(SV)":[11],"systems.":[12,120],"These":[13],"challenges":[14],"can":[15],"be":[16],"addressed":[17],"using":[18,92],"a":[19,24,49,58,64,70,77],"speech":[20,39,60],"enhancement":[21,40,61],"system":[22,62],"as":[23],"front-end":[25],"module.":[26],"Recently,":[27],"diffusion":[28],"probabilistic":[29],"models":[30],"(DPMs)":[31],"have":[32],"exhibited":[33],"remarkable":[34],"noise-compensation":[35],"capabilities":[36],"in":[37],"domain.":[41],"Building":[42],"on":[43],"this":[44],"success,":[45],"we":[46],"propose":[47],"Diff-SV,":[48],"noise-robust":[50,118],"SV":[51,119],"framework":[52],"that":[53,110],"leverages":[54],"DPM.":[55],"Diff-SV":[56,111],"unifies":[57],"DPM-based":[59],"with":[63],"embedding":[66],"extractor,":[67],"yields":[69],"discriminative":[71],"noise-tolerable":[73],"representation":[75],"through":[76],"hierarchical":[78],"structure.":[79],"The":[80,105],"proposed":[81,117],"model":[82],"was":[83],"evaluated":[84],"under":[85],"both":[86],"in-domain":[87],"out-of-domain":[89],"noisy":[90],"conditions":[91],"VoxCeleb1":[94],"test":[95],"set,":[96],"an":[97],"external":[98],"source,":[100],"VOiCES":[103],"corpus.":[104],"obtained":[106],"experimental":[107],"results":[108],"demonstrate":[109],"achieves":[112],"state-of-the-art":[113],"performance,":[114],"outperforming":[115],"recently":[116]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}