{"id":"https://openalex.org/W4408352666","doi":"https://doi.org/10.1109/icassp49660.2025.10887814","title":"Grouped Knowledge Distillation with Adaptive Logit Softening for Speaker Recognition","display_name":"Grouped Knowledge Distillation with Adaptive Logit Softening for Speaker Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352666","doi":"https://doi.org/10.1109/icassp49660.2025.10887814"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887814","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/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":true,"raw_author_name":"Chong-Xin Gan","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR","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,Department of Electrical and Electronic Engineering,Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","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":false,"raw_author_name":"Zezhong Jin","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","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,Department of Electrical and Electronic Engineering,Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"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":"Kong Aik Lee","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104260046"],"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":0.05020662,"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/T10860","display_name":"Speech and Audio Processing","score":0.9652000069618225,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9652000069618225,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9569000005722046,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9301999807357788,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6399221420288086},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.615828812122345},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6089400053024292},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4778282642364502},{"id":"https://openalex.org/keywords/softening","display_name":"Softening","score":0.44917768239974976},{"id":"https://openalex.org/keywords/logit","display_name":"Logit","score":0.4342893362045288},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.4192691743373871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3721657991409302},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3373834490776062},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23700517416000366},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17690256237983704},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1497778594493866},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.057030171155929565}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6399221420288086},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.615828812122345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6089400053024292},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4778282642364502},{"id":"https://openalex.org/C2781098093","wikidata":"https://www.wikidata.org/wiki/Q85787439","display_name":"Softening","level":2,"score":0.44917768239974976},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.4342893362045288},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.4192691743373871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3721657991409302},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3373834490776062},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23700517416000366},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17690256237983704},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1497778594493866},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.057030171155929565},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887814","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2888968865","https://openalex.org/W2890964092","https://openalex.org/W2919115771","https://openalex.org/W2936733796","https://openalex.org/W2962788625","https://openalex.org/W2981087920","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3039832962","https://openalex.org/W3095079700","https://openalex.org/W3137249133","https://openalex.org/W3163505255","https://openalex.org/W3197580070","https://openalex.org/W3198804855","https://openalex.org/W3205635414","https://openalex.org/W3206189675","https://openalex.org/W3206886023","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4226426325","https://openalex.org/W4295789112","https://openalex.org/W4297841773","https://openalex.org/W4372340947","https://openalex.org/W4375869145","https://openalex.org/W4382450293","https://openalex.org/W4385823178","https://openalex.org/W4388820649","https://openalex.org/W4391423796","https://openalex.org/W4392903919","https://openalex.org/W4392908937","https://openalex.org/W4402111729","https://openalex.org/W6638523607","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2514442859","https://openalex.org/W1573454649","https://openalex.org/W2464639917","https://openalex.org/W2491173004","https://openalex.org/W2150348631","https://openalex.org/W2375064432","https://openalex.org/W2363110606","https://openalex.org/W2077865273","https://openalex.org/W2559245114","https://openalex.org/W1989125082"],"abstract_inverted_index":{"Recent":[0],"works":[1],"suggest":[2],"that":[3,11],"decoupling":[4],"the":[5,13,23,67,77,89,97,111,117,151],"information":[6],"of":[7,12,76,140],"non-target":[8,40],"speakers":[9],"from":[10],"target":[14],"speaker":[15,41,72,78],"in":[16,50,81,116],"knowledge":[17,47,63,80,123],"distillation":[18,64],"(KD)":[19],"and":[20,99,113,143],"subsequently":[21],"emphasizing":[22],"former":[24],"can":[25],"lead":[26],"to":[27,46,88,109],"significant":[28],"performance":[29],"improvement.":[30],"However,":[31],"a":[32,51,61,92,130,155],"well-trained":[33],"teacher":[34],"model":[35],"typically":[36],"produces":[37],"almost":[38],"zero":[39],"posteriors":[42,73],"with":[43,70,129,154],"limited":[44],"contribution":[45],"transfer,":[48],"resulting":[49],"less":[52],"effective":[53,122],"KD.":[54],"To":[55],"address":[56],"this":[57],"problem,":[58],"we":[59],"advocate":[60],"dual-group":[62],"framework,":[65],"wherein":[66],"primary":[68,98],"group":[69,86],"top-k":[71],"captures":[74],"most":[75],"discrimination":[79],"an":[82,135],"utterance.":[83],"The":[84,125],"non-primary":[85,100],"contributes":[87],"KD":[90],"through":[91],"binary":[93,118],"classification":[94],"(distillation)":[95],"between":[96],"groups.":[101],"In":[102],"addition,":[103],"adaptive":[104],"logit":[105],"softening":[106],"is":[107],"proposed":[108,126],"adjust":[110],"teacher\u2019s":[112],"student\u2019s":[114],"logits":[115],"distillation,":[119],"further":[120],"facilitating":[121],"transfer.":[124],"method":[127],"trained":[128],"simple":[131],"x-vector":[132],"pipeline":[133],"obtains":[134],"impressive":[136],"equal":[137],"error":[138],"rate":[139],"1.46%,":[141],"1.47%,":[142],"2.70%":[144],"on":[145],"three":[146],"VoxCeleb1":[147],"test":[148],"sets,":[149],"outperforming":[150],"state-of-the-art":[152],"methods":[153],"noticeable":[156],"margin.":[157]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}