{"id":"https://openalex.org/W7165674591","doi":"https://doi.org/10.48550/arxiv.2606.21215","title":"Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach","display_name":"Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach","publication_year":2026,"publication_date":"2026-06-19","ids":{"openalex":"https://openalex.org/W7165674591","doi":"https://doi.org/10.48550/arxiv.2606.21215"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2606.21215","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.21215","pdf_url":"https://arxiv.org/pdf/2606.21215","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/2606.21215","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143527919","display_name":"Tzu-Chieh Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei, Tzu-Chieh","raw_affiliation_strings":["University of Michigan , USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan , USA,","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139151637","display_name":"Yi-Cheng Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lin, Yi-Cheng","raw_affiliation_strings":["National Taiwan University , Taipei , Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University , Taipei , Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089273852","display_name":"Huang-Cheng Chou","orcid":"https://orcid.org/0000-0003-2125-5689","observed_orcids":["https://orcid.org/0000-0003-2125-5689"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chou, Huang-Cheng","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory (SAIL) , University of Southern California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory (SAIL) , University of Southern California , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135385002","display_name":"Kuan-Yu Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chen, Kuan-Yu","raw_affiliation_strings":["National Taiwan University , Taipei , Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University , Taipei , Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090371482","display_name":"Hsin-Yen Sung","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sung, Hsin-Yen","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory (SAIL) , University of Southern California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory (SAIL) , University of Southern California , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128636623","display_name":"Shrikanth Narayanan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Narayanan, Shrikanth","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory (SAIL) , University of Southern California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory (SAIL) , University of Southern California , USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139212885","display_name":"Hung-yi Lee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lee, Hung-yi","raw_affiliation_strings":["National Taiwan University , Taipei , Taiwan","National Taiwan University Artificial Intelligence Center of Research Excellence , Taipei , Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University , Taipei , Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University Artificial Intelligence Center of Research Excellence , Taipei , Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"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":true,"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":0.9990000128746033,"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":0.9990000128746033,"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":0.0003000000142492354,"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/T10828","display_name":"Biometric Identification and Security","score":9.999999747378752e-05,"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/nonverbal-vocalizations","display_name":"nonverbal vocalizations","score":0.9070000052452087},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"speaker verification","score":0.9240000247955322},{"id":"https://openalex.org/keywords/catastrophic-forgetting","display_name":"catastrophic forgetting","score":0.6470000147819519},{"id":"https://openalex.org/keywords/mixture-of-experts","display_name":"mixture of experts","score":0.9940000176429749},{"id":"https://openalex.org/keywords/data2vec","display_name":"data2vec","score":0.7850000262260437},{"id":"https://openalex.org/keywords/ecapa-tdnn","display_name":"ECAPA-TDNN","score":0.9729999899864197},{"id":"https://openalex.org/keywords/contrastive-loss","display_name":"contrastive loss","score":0.7329999804496765},{"id":"https://openalex.org/keywords/expressive-text-to-speech","display_name":"expressive text-to-speech","score":0.8209999799728394},{"id":"https://openalex.org/keywords/voice-conversion","display_name":"voice conversion","score":0.9229999780654907},{"id":"https://openalex.org/keywords/domain-gap","display_name":"domain gap","score":0.5170000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.710099995136261},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6402999758720398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6247000098228455},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6189000010490417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49799999594688416},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4948999881744385},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46970000863075256},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30059999227523804},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2606.21215","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.21215","pdf_url":"https://arxiv.org/pdf/2606.21215","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.2606.21215","doi":"https://doi.org/10.48550/arxiv.2606.21215","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.21215","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.21215","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.21215","pdf_url":"https://arxiv.org/pdf/2606.21215","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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4505413760","display_name":null,"funder_award_id":"D2023-2308110001","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"},{"id":"https://openalex.org/G4816118824","display_name":"RI Core: Medium: Structured variability in vocal tract articulation dynamics in speech","funder_award_id":"2311676","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7165674591.pdf","grobid_xml":"https://content.openalex.org/works/W7165674591.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7214040657","https://openalex.org/W7213265561","https://openalex.org/W1973922236","https://openalex.org/W4283703905","https://openalex.org/W2651834199","https://openalex.org/W2938804447","https://openalex.org/W167150455","https://openalex.org/W7138353318","https://openalex.org/W7084103406","https://openalex.org/W1551249178"],"abstract_inverted_index":{"As":[0],"expressive":[1],"text-to-speech":[2],"(TTS)":[3],"and":[4,31,42,63,122],"voice":[5],"conversion":[6],"(VC)":[7],"systems":[8,37],"increasingly":[9],"generate":[10],"non-verbal":[11,32],"vocalizations":[12],"(NVVs)":[13],"to":[14,23,40,116,128],"enhance":[15],"naturalness,":[16],"reliable":[17],"speaker":[18],"verification":[19],"(SV)":[20],"becomes":[21],"essential":[22],"objectively":[24],"assess":[25],"identity":[26],"consistency":[27],"across":[28,59],"both":[29],"verbal":[30],"segments.":[33],"Yet":[34],"current":[35],"SV":[36],"generalize":[38],"poorly":[39],"NVVs,":[41],"fine-tuning":[43],"on":[44,90],"NVV":[45,61],"data":[46],"causes":[47],"catastrophic":[48],"forgetting":[49],"of":[50,78],"speech":[51,91,124],"performance.":[52],"We":[53],"present":[54],"the":[55,105],"first":[56],"systematic":[57],"study":[58],"10":[60],"types":[62],"propose":[64],"a":[65,76,94,101,119],"framework":[66],"combining":[67],"frozen":[68],"Data2Vec":[69],"self-supervised":[70],"features":[71],"with":[72,82],"ECAPA-TDNN,":[73],"enhanced":[74],"by":[75],"Mixture":[77],"Experts":[79],"(MoE)":[80],"module":[81],"learned":[83],"domain-aware":[84],"routing.":[85],"A":[86],"conditional":[87],"distillation":[88],"loss":[89,103],"inputs":[92],"via":[93,130],"pretrained":[95,120],"teacher":[96],"retains":[97],"speech-to-speech":[98],"accuracy,":[99],"while":[100],"contrastive":[102],"bridges":[104],"speech-NVV":[106,112],"domain":[107],"gap.":[108],"Our":[109],"method":[110],"reduces":[111],"EER":[113,125],"from":[114,126],"38.93%":[115],"22.66%":[117],"over":[118],"baseline,":[121],"improves":[123],"13.17%":[127],"9.24%":[129],"distillation.":[131]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-06-24T00:00:00"}