{"id":"https://openalex.org/W4415433933","doi":"https://doi.org/10.21437/interspeech.2025-494","title":"Variability in performance across four generations of automatic speaker recognition systems","display_name":"Variability in performance across four generations of automatic speaker recognition systems","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433933","doi":"https://doi.org/10.21437/interspeech.2025-494"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-494","doi":"https://doi.org/10.21437/interspeech.2025-494","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-494","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.whiterose.ac.uk/id/eprint/226964/1/ASR_Interspeech_25_final_1_.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103188600","display_name":"Lauren Harrington","orcid":"https://orcid.org/0000-0003-0357-159X","observed_orcids":["https://orcid.org/0000-0003-0357-159X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lauren Harrington","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059606221","display_name":"Vincent Hughes","orcid":"https://orcid.org/0000-0002-4660-979X","observed_orcids":["https://orcid.org/0000-0002-4660-979X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Hughes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072775877","display_name":"Philip Harrison","orcid":"https://orcid.org/0000-0003-2419-2388","observed_orcids":["https://orcid.org/0000-0003-2419-2388"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philip Harrison","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055401924","display_name":"Paul Foulkes","orcid":"https://orcid.org/0000-0001-9481-1004","observed_orcids":["https://orcid.org/0000-0001-9481-1004"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Foulkes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016449234","display_name":"Jessica Wormald","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jessica Wormald","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087883012","display_name":"Finnian Kelly","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Finnian Kelly","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012244413","display_name":"David van der Vloed","orcid":"https://orcid.org/0000-0003-4600-451X","observed_orcids":["https://orcid.org/0000-0003-4600-451X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David van der Vloed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3567,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54602513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3993","last_page":"3997"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"speaker recognition","score":0.9800000190734863},{"id":"https://openalex.org/keywords/i-vectors","display_name":"i-vectors","score":0.6470000147819519},{"id":"https://openalex.org/keywords/x-vector","display_name":"x-vector","score":0.996999979019165},{"id":"https://openalex.org/keywords/ecapa-tdnn","display_name":"ECAPA-TDNN","score":0.8970000147819519},{"id":"https://openalex.org/keywords/gmm-ubm","display_name":"GMM-UBM","score":0.9190000295639038},{"id":"https://openalex.org/keywords/forensic-speaker-recognition","display_name":"forensic speaker identification","score":0.6700000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5773000121116638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5525000095367432},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40880000591278076},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C117623542","wikidata":"https://www.wikidata.org/wiki/Q621974","display_name":"Automatic target recognition","level":3,"score":0.24529999494552612}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-494","doi":"https://doi.org/10.21437/interspeech.2025-494","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-494","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:226964","doi":null,"is_oa":true,"landing_page_url":"https://eprints.whiterose.ac.uk/id/eprint/226964/","pdf_url":"https://eprints.whiterose.ac.uk/id/eprint/226964/1/ASR_Interspeech_25_final_1_.pdf","source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Proceedings Paper"}],"best_oa_location":{"id":"pmh:oai:eprints.whiterose.ac.uk:226964","doi":null,"is_oa":true,"landing_page_url":"https://eprints.whiterose.ac.uk/id/eprint/226964/","pdf_url":"https://eprints.whiterose.ac.uk/id/eprint/226964/1/ASR_Interspeech_25_final_1_.pdf","source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Proceedings Paper"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433933.pdf","grobid_xml":"https://content.openalex.org/works/W4415433933.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4400615854","https://openalex.org/W2072245643","https://openalex.org/W7169618975","https://openalex.org/W6959825181","https://openalex.org/W4386479643","https://openalex.org/W131864997","https://openalex.org/W7155709846","https://openalex.org/W6941856738","https://openalex.org/W7043183799","https://openalex.org/W3083828098"],"abstract_inverted_index":{"The":[0],"field":[1,47],"of":[2,11,23,65,68,75,120,133],"automatic":[3],"speaker":[4,15],"recognition":[5],"(ASR)":[6],"has":[7,26],"seen":[8],"a":[9,81],"series":[10],"generational":[12],"changes":[13],"to":[14,90,92,104,117],"modelling":[16],"approaches":[17,25],"in":[18,33],"the":[19,46,63,72,118],"last":[20],"3":[21],"decades.Adoption":[22],"new":[24],"mainly":[27],"been":[28],"driven":[29],"by":[30],"improvements":[31,87],"observed":[32],"overall":[34],"system-level":[35],"performance":[36,64,119],"metrics":[37],"on":[38],"common":[39],"datasets.There":[40],"is":[41],"now":[42],"considerable":[43],"debate":[44],"within":[45],"around":[48],"understanding":[49],"why":[50],"systems":[51,70,124],"perform":[52],"better":[53],"for":[54,96,129],"some":[55],"speakers":[56,122],"than":[57],"others.In":[58],"this":[59],"study,":[60],"we":[61,85],"compare":[62],"4":[66],"generations":[67],"ASR":[69],"with":[71],"same":[73],"set":[74],"forensically-relevant":[76],"test":[77],"and":[78,123],"calibration":[79],"data.On":[80],"system-and":[82],"individual":[83,121],"speaker-level,":[84],"observe":[86],"from":[88],"GMM-UBM":[89],"i-vector":[91],"x-vector":[93],"but":[94],"not":[95],"ECAPA-TDNN.We":[97],"find":[98],"that":[99,111],"certain":[100],"individuals":[101],"remain":[102],"difficult":[103],"recognise":[105],"across":[106],"all":[107],"systems.Our":[108],"findings":[109],"show":[110],"both":[112],"file-and":[113],"speaker-level":[114],"factors":[115],"contribute":[116],"overall,":[125],"which":[126],"supports":[127],"calls":[128],"more":[130],"detailed":[131],"exploration":[132],"system":[134],"performance.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2025-10-24T00:00:00"}