{"id":"https://openalex.org/W4408354128","doi":"https://doi.org/10.1109/icassp49660.2025.10889980","title":"Denoising Student Features with Diffusion Models for Knowledge Distillation in Speaker Verification","display_name":"Denoising Student Features with Diffusion Models for Knowledge Distillation in Speaker Verification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354128","doi":"https://doi.org/10.1109/icassp49660.2025.10889980"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5111193687","display_name":"Zezhong Jin","orcid":"https://orcid.org/0009-0001-0828-2933"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zezhong Jin","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019467579","display_name":"Youzhi Tu","orcid":"https://orcid.org/0000-0002-9580-2414"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Youzhi Tu","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671772","display_name":"Zhe Li","orcid":"https://orcid.org/0000-0003-4176-9687"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhe Li","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101462087","display_name":"Zilong Huang","orcid":"https://orcid.org/0000-0002-6744-0671"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zilong Huang","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104260046","display_name":"Chong-Xin Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chong-Xin Gan","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5111193687"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02059887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9843000173568726,"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":0.9843000173568726,"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":0.9337999820709229,"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":0.7480276226997375},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6685468554496765},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5861451029777527},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5530228018760681},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5355871319770813},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5163854360580444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36916738748550415},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.36132383346557617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480276226997375},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6685468554496765},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5861451029777527},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5530228018760681},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5355871319770813},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5163854360580444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36916738748550415},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.36132383346557617},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2136682440","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2888968865","https://openalex.org/W2890964092","https://openalex.org/W2962788625","https://openalex.org/W2972743990","https://openalex.org/W3010925296","https://openalex.org/W3024869864","https://openalex.org/W3198275944","https://openalex.org/W3206189675","https://openalex.org/W3206886023","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4206908380","https://openalex.org/W4221154745","https://openalex.org/W4226426325","https://openalex.org/W4387790227","https://openalex.org/W4392908937","https://openalex.org/W4400033122","https://openalex.org/W4408352172","https://openalex.org/W6631362777","https://openalex.org/W6638523607","https://openalex.org/W6688816777","https://openalex.org/W6779823529","https://openalex.org/W6780218876","https://openalex.org/W6783713337","https://openalex.org/W6853142820"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"there":[3],"has":[4],"been":[5],"a":[6,12,17,32,36,45,93,115,119],"surge":[7],"in":[8,58,69],"the":[9,41,56,61,72,78,98,123,126,132],"use":[10],"of":[11],"pre-trained":[13,33],"speech":[14],"model":[15,26,34,59,95],"as":[16],"feature":[18],"extractor":[19],"for":[20,101,140],"speaker":[21],"verification":[22],"(SV).":[23],"To":[24,87],"reduce":[25],"complexity,":[27],"researchers":[28],"transfer":[29],"knowledge":[30,84],"from":[31],"to":[35,43,55,96,137],"lightweight":[37],"student":[38,62,75,99],"model,":[39],"enabling":[40],"latter":[42],"reach":[44],"performance":[46],"level":[47],"not":[48],"attainable":[49],"by":[50],"conventional":[51],"methods.":[52],"However,":[53],"due":[54],"differences":[57],"capacity,":[60],"features":[63,76,100],"contain":[64],"more":[65,107],"noise.":[66],"This":[67,104],"results":[68],"discrepancies":[70],"between":[71],"teacher":[73],"and":[74],"at":[77],"intermediate":[79],"layers,":[80],"negatively":[81],"impacting":[82],"feature-level":[83,109],"distillation":[85],"(KD).":[86],"address":[88],"this":[89],"issue,":[90],"we":[91],"employ":[92],"diffusion":[94],"denoise":[97],"KD":[102],"(DenoKD).":[103],"approach":[105],"enables":[106],"effective":[108,139],"distillation.":[110],"Our":[111],"method,":[112],"trained":[113],"with":[114],"small":[116],"ECAPA-TDNN,":[117],"achieved":[118],"13%":[120],"improvement":[121],"over":[122],"baseline":[124],"on":[125,142],"VoxCeleb1-O":[127],"test":[128,144],"set.":[129],"Further":[130],"more,":[131],"DenoKD":[133],"mechanism":[134],"is":[135],"found":[136],"be":[138],"SV":[141],"short":[143],"utterances.":[145]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
