{"id":"https://openalex.org/W4408354634","doi":"https://doi.org/10.1109/icassp49660.2025.10889147","title":"Fast Adaptation of Pretrained Speaker Verification System for Source Speaker Tracking","display_name":"Fast Adaptation of Pretrained Speaker Verification System for Source Speaker Tracking","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354634","doi":"https://doi.org/10.1109/icassp49660.2025.10889147"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889147","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":"https://openalex.org/A5081813105","display_name":"Xiang Lyu","orcid":"https://orcid.org/0000-0002-0015-3061"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Lyu","raw_affiliation_strings":["Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375986","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0002-5743-2029"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091510097","display_name":"Tianyu Zhao","orcid":"https://orcid.org/0000-0003-4784-5919"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyu Zhao","raw_affiliation_strings":["Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070862393","display_name":"Huadai Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huadai Liu","raw_affiliation_strings":["Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9818999767303467,"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":0.9818999767303467,"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":0.972000002861023,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9528999924659729,"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":0.8046056628227234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.734809935092926},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7137033343315125},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6759294271469116},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6740772724151611},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6339415311813354},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4224299490451813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4053170084953308},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.04929375648498535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046056628227234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.734809935092926},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7137033343315125},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6759294271469116},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6740772724151611},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6339415311813354},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4224299490451813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4053170084953308},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.04929375648498535},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889147","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":2,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W3209984917"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W3141593045","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Traditional":[0],"speaker":[1,7,47,52],"verification":[2,48],"system":[3,89,106],"aims":[4],"at":[5],"distinguish":[6],"identity":[8],"in":[9,18,76,96,102],"real":[10,77],"world":[11,78],"audio,":[12],"and":[13,27,58,98],"has":[14],"achieved":[15],"satisfying":[16],"performance":[17,75],"many":[19],"scenarios.":[20],"However,":[21],"it":[22],"is":[23],"also":[24],"very":[25],"vulnerable,":[26],"can":[28],"be":[29],"easily":[30],"attacked":[31],"by":[32,94],"voice":[33,67,104],"anonymization":[34,68,105],"system.":[35],"In":[36],"this":[37],"report,":[38],"we":[39],"describe":[40],"how":[41],"to":[42,50],"fast":[43],"adapt":[44],"a":[45],"pretrained":[46,56],"model":[49],"source":[51],"tracking":[53],"task":[54],"with":[55],"feature":[57],"Lora":[59],"[1]":[60],"technique.":[61],"It":[62],"significantly":[63],"reduce":[64,91],"EER":[65,93,101],"on":[66,82],"system,":[69],"as":[70,72],"well":[71],"keep":[73],"its":[74],"audio":[79],"intact.":[80],"Experiment":[81],"Attacker":[83],"Challenge":[84],"[2]":[85],"shows":[86],"that":[87],"our":[88],"successfully":[90],"baseline":[92],"32%":[95],"average,":[97],"achieve":[99],"lowest":[100],"all":[103],"except":[107],"T8-5.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
