{"id":"https://openalex.org/W4408355810","doi":"https://doi.org/10.1109/icassp49660.2025.10887949","title":"A Study of Multi-Scale Feature Learning From Pre-Trained Models on Speaker Verification","display_name":"A Study of Multi-Scale Feature Learning From Pre-Trained Models on Speaker Verification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355810","doi":"https://doi.org/10.1109/icassp49660.2025.10887949"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887949","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":"conference-paper","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":null,"display_name":"Shengyu Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyu Peng","raw_affiliation_strings":["University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604078","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-0530-3954"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107955159","display_name":"Zuoliang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuoliang Li","raw_affiliation_strings":["University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084397928","display_name":"Yu Guan","orcid":"https://orcid.org/0000-0002-7833-9755"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Guan","raw_affiliation_strings":["University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101875578","display_name":"Bin Gu","orcid":"https://orcid.org/0000-0003-1621-7311"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Gu","raw_affiliation_strings":["University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"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":0.9872000217437744,"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":0.9872000217437744,"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":0.9021999835968018,"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":0.830490231513977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8183143734931946},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6191465854644775},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5656164884567261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5604096055030823},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5600646734237671},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.554207980632782},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4231051206588745},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40356960892677307}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.830490231513977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8183143734931946},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6191465854644775},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5656164884567261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5604096055030823},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5600646734237671},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.554207980632782},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4231051206588745},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40356960892677307},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887949","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":[{"score":0.4699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W125553504","https://openalex.org/W2157161740","https://openalex.org/W2194775991","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2928165649","https://openalex.org/W2938358845","https://openalex.org/W2969985801","https://openalex.org/W3010893827","https://openalex.org/W3024869864","https://openalex.org/W3197111314","https://openalex.org/W3198275944","https://openalex.org/W3198777143","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4206285316","https://openalex.org/W4226380987","https://openalex.org/W4313590886","https://openalex.org/W4319862271","https://openalex.org/W4385822451","https://openalex.org/W4385822752","https://openalex.org/W4385822954","https://openalex.org/W4385823178","https://openalex.org/W4385823373","https://openalex.org/W4386702814","https://openalex.org/W4390168362","https://openalex.org/W4392263008","https://openalex.org/W4392902960","https://openalex.org/W4392903636","https://openalex.org/W4400033122","https://openalex.org/W6688816777","https://openalex.org/W6737575990","https://openalex.org/W6780218876","https://openalex.org/W6784256521"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,25,35],"multi-scale":[4,68],"feature":[5,27,39,75],"fusion":[6],"paradigm":[7],"is":[8],"proposed":[9,102],"to":[10,65,87],"fully":[11],"exploit":[12],"the":[13,16,45,51,55,59,67,74,81,89,98,101,113,119],"power":[14],"of":[15,44,54,58,73,100,108,116],"pre-trained":[17,60,123],"models":[18],"for":[19],"text-independent":[20],"speaker":[21,91],"verification.":[22],"It":[23],"contains":[24],"front-end":[26],"extractor":[28,40,76],"and":[29,110,121],"an":[30],"enhanced":[31],"ECAPA-TDNN":[32],"backend":[33],"in":[34],"cascade":[36],"manner.":[37],"The":[38,71],"incorporates":[41],"local":[42],"representations":[43],"CNN":[46],"layers":[47,57],"as":[48,50],"well":[49],"global":[52],"clues":[53],"Transformer":[56],"models,":[61,124],"which":[62],"are":[63,77],"combined":[64],"construct":[66],"discriminative":[69],"features.":[70],"outputs":[72],"then":[78],"fed":[79],"into":[80],"back-end":[82],"model":[83],"(tailored":[84],"from":[85],"ECAPA-TDNN)":[86],"obtain":[88],"final":[90],"embedding.":[92],"Results":[93],"on":[94,112],"VoxCeleb":[95],"datasets":[96],"validate":[97],"superiority":[99],"method":[103],"with":[104],"equal":[105],"error":[106],"rates":[107],"0.633%":[109],"0.457%":[111],"official":[114],"trials":[115],"Vox1-O":[117],"using":[118],"base":[120],"large":[122],"respectively.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}