{"id":"https://openalex.org/W4408353632","doi":"https://doi.org/10.1109/icassp49660.2025.10887848","title":"Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels","display_name":"Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353632","doi":"https://doi.org/10.1109/icassp49660.2025.10887848"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887848","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/A5090927958","display_name":"Zakaria Aldeneh","orcid":"https://orcid.org/0000-0003-4599-2448"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zakaria Aldeneh","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101768343","display_name":"Takuya Higuchi","orcid":"https://orcid.org/0000-0002-0361-7132"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Takuya Higuchi","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091834525","display_name":"Jee-weon Jung","orcid":"https://orcid.org/0000-0003-0505-2988"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jee-Weon Jung","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625784","display_name":"Liwei Chen","orcid":"https://orcid.org/0000-0002-9858-0765"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li-Wei Chen","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021880697","display_name":"Stephen Shum","orcid":"https://orcid.org/0000-0001-7292-8121"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stephen Shum","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101807751","display_name":"Ahmed Hussen Abdelaziz","orcid":"https://orcid.org/0000-0001-8027-4666"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ahmed Hussen Abdelaziz","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106542588","display_name":"Tatiana Likhomanenko","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tatiana Likhomanenko","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112911728","display_name":"Barry-John Theobald","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Barry-John Theobald","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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":0.9925000071525574,"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":0.9925000071525574,"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":0.9470999836921692,"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-diarisation","display_name":"Speaker diarisation","score":0.8194904923439026},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.75752854347229},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7429835796356201},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6644025444984436},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5692854523658752},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.535156786441803},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.47501930594444275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4678436517715454},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38378408551216125}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8194904923439026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75752854347229},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7429835796356201},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6644025444984436},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5692854523658752},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.535156786441803},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.47501930594444275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4678436517715454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38378408551216125}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887848","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":31,"referenced_works":["https://openalex.org/W2101234009","https://openalex.org/W2150769028","https://openalex.org/W2395750323","https://openalex.org/W2696967604","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W3024869864","https://openalex.org/W3096338464","https://openalex.org/W3163187953","https://openalex.org/W3205635414","https://openalex.org/W3209059054","https://openalex.org/W4221154745","https://openalex.org/W4290712827","https://openalex.org/W4290995108","https://openalex.org/W4297841773","https://openalex.org/W4319862473","https://openalex.org/W4372260593","https://openalex.org/W4372346385","https://openalex.org/W4385823202","https://openalex.org/W4388579618","https://openalex.org/W4392902934","https://openalex.org/W4392904518","https://openalex.org/W4392910494","https://openalex.org/W4402111799","https://openalex.org/W4408353935","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6769178842","https://openalex.org/W6784400926","https://openalex.org/W6810673746","https://openalex.org/W6861295083"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W4401661962","https://openalex.org/W4247736853","https://openalex.org/W1521049138","https://openalex.org/W2144470400","https://openalex.org/W2997340161","https://openalex.org/W2911612049","https://openalex.org/W1589374915"],"abstract_inverted_index":{"Iterative":[0],"self-training,":[1],"or":[2],"iterative":[3],"pseudo-labeling":[4],"(IPL)\u2014using":[5],"an":[6],"improved":[7],"model":[8,93,149],"from":[9,45],"the":[10,17,28,86,98,102,112,118,123,126,129,134],"current":[11],"iteration":[12],"to":[13,21,26,69,96],"provide":[14],"pseudo-labels":[15],"for":[16,101],"next":[18],"iteration\u2014has":[19],"proven":[20],"be":[22,76],"a":[23,143],"powerful":[24],"approach":[25],"enhance":[27],"quality":[29],"of":[30,35,105,114,131],"speaker":[31,39,106,156],"representations.":[32,107],"Recent":[33],"applications":[34],"IPL":[36,99,119,152],"in":[37],"unsupervised":[38,103],"recognition":[40],"start":[41],"with":[42,142],"representations":[43],"extracted":[44],"very":[46],"elaborate":[47],"self-supervised":[48,56],"methods":[49],"(e.g.,":[50],"DINO).":[51],"However,":[52],"training":[53],"such":[54],"strong":[55],"models":[57],"is":[58,94],"not":[59,67,75],"straightforward":[60],"(they":[61],"require":[62],"hyper-parameter":[63],"tuning":[64],"and":[65,89,133,145],"may":[66,74],"generalize":[68],"out-of-domain":[70],"data)":[71],"and,":[72],"moreover,":[73],"needed":[77],"at":[78],"all.":[79],"To":[80],"this":[81],"end,":[82],"we":[83,138],"show":[84],"that":[85,140,159],"simple,":[87],"well-studied,":[88],"established":[90],"i-vector":[91],"generative":[92],"enough":[95],"bootstrap":[97],"process":[100],"learning":[104],"We":[108],"also":[109],"systematically":[110],"study":[111],"impact":[113],"other":[115],"components":[116],"on":[117],"process,":[120],"which":[121],"includes":[122],"initial":[124,148],"model,":[125],"encoder,":[127],"augmentations,":[128],"number":[130],"clusters,":[132],"clustering":[135],"algorithm.":[136],"Remarkably,":[137],"find":[139],"even":[141],"simple":[144],"significantly":[146],"weaker":[147],"like":[150],"i-vector,":[151],"can":[153],"still":[154],"achieve":[155],"verification":[157],"performance":[158],"rivals":[160],"state-of-the-art":[161],"methods.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}