{"id":"https://openalex.org/W7151996232","doi":"https://doi.org/10.48550/arxiv.2604.05201","title":"Exploring Speech Foundation Models for Speaker Diarization Across Lifespan","display_name":"Exploring Speech Foundation Models for Speaker Diarization Across Lifespan","publication_year":2026,"publication_date":"2026-04-06","ids":{"openalex":"https://openalex.org/W7151996232","doi":"https://doi.org/10.48550/arxiv.2604.05201"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2604.05201","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.05201","pdf_url":"https://arxiv.org/pdf/2604.05201","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2604.05201","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128877595","display_name":"Anfeng Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Anfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128663831","display_name":"Tiantian Feng","orcid":"https://orcid.org/0000-0002-2053-9068","observed_orcids":["https://orcid.org/0000-0002-2053-9068"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Tiantian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Shri Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204","observed_orcids":["https://orcid.org/0000-0002-1052-6204"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Narayanan, Shrikanth","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"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":0.9945999979972839,"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":0.0035000001080334187,"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/T12031","display_name":"Speech and dialogue systems","score":0.0010000000474974513,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-foundation-models","display_name":"speech foundation models","score":0.906000018119812},{"id":"https://openalex.org/keywords/speaker-diarization","display_name":"speaker diarization","score":0.996999979019165},{"id":"https://openalex.org/keywords/children-s-speech","display_name":"children's speech","score":0.6060000061988831},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.8149999976158142},{"id":"https://openalex.org/keywords/end-to-end-neural-diarization","display_name":"end-to-end neural diarization","score":0.8960000276565552}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8375999927520752},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6266000270843506},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.6219000220298767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5878000259399414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5874999761581421},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3073999881744385},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C2989496772","wikidata":"https://www.wikidata.org/wiki/Q52946","display_name":"Speech communication","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.25859999656677246}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2604.05201","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.05201","pdf_url":"https://arxiv.org/pdf/2604.05201","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2604.05201","doi":"https://doi.org/10.48550/arxiv.2604.05201","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.05201","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2604.05201","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.05201","pdf_url":"https://arxiv.org/pdf/2604.05201","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.7245074510574341}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speech":[0],"foundation":[1],"models":[2,55,72],"have":[3],"shown":[4],"strong":[5],"transferability":[6],"across":[7,89],"a":[8,31,35],"wide":[9],"range":[10],"of":[11],"speech":[12,43,76],"applications.":[13],"However,":[14],"their":[15],"robustness":[16,94],"to":[17,79],"age-related":[18],"domain":[19],"shift":[20],"in":[21,99,111],"speaker":[22],"diarization":[23,39,97,112],"remains":[24],"underexplored.":[25],"In":[26],"this":[27],"work,":[28],"we":[29],"present":[30],"cross-lifespan":[32],"evaluation":[33],"within":[34],"unified":[36],"end-to-end":[37],"neural":[38],"framework":[40],"(EEND-VC),":[41],"covering":[42],"samples":[44],"from":[45],"conversations":[46],"involving":[47],"children,":[48],"adults,":[49],"and":[50,63,81],"older":[51],"adults.":[52],"We":[53],"compare":[54],"under":[56],"zero-shot":[57],"cross-age":[58],"inference,":[59],"joint":[60,86],"multi-age":[61,87],"training,":[62],"domain-specific":[64],"adaptation.":[65],"Results":[66],"show":[67],"substantial":[68],"performance":[69,98],"degradation":[70],"when":[71,115],"trained":[73],"on":[74],"adult-specific":[75],"are":[77],"applied":[78],"child":[80],"older-adult":[82],"conversational":[83],"data.":[84],"Moreover,":[85],"training":[88],"different":[90],"age":[91,105],"groups":[92],"improves":[93],"without":[95],"reducing":[96],"canonical":[100],"adult":[101],"conversations,":[102],"while":[103],"targeted":[104],"group":[106],"adaptation":[107],"yields":[108],"further":[109],"gains":[110],"performance,":[113],"particularly":[114],"using":[116],"the":[117],"Whisper":[118],"encoder.":[119]},"counts_by_year":[],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2026-04-09T00:00:00"}