{"id":"https://openalex.org/W7148571800","doi":"https://doi.org/10.1109/asru65441.2025.11434741","title":"Emotional Styles Hide in Deep Speaker Embeddings: Disentangle Deep Speaker Embeddings for Speaker Clustering","display_name":"Emotional Styles Hide in Deep Speaker Embeddings: Disentangle Deep Speaker Embeddings for Speaker Clustering","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148571800","doi":"https://doi.org/10.1109/asru65441.2025.11434741"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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/A5028246785","display_name":"Chaohao Lin","orcid":"https://orcid.org/0000-0001-9737-8007"},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chaohao Lin","raw_affiliation_strings":["Florida International University,Electrical and Computer Engineering,Miami,USA"],"affiliations":[{"raw_affiliation_string":"Florida International University,Electrical and Computer Engineering,Miami,USA","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100944258","display_name":"Xu Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Zheng","raw_affiliation_strings":["Florida International University,Knight Foundation School of Computing and Information Sciences,Miami,USA"],"affiliations":[{"raw_affiliation_string":"Florida International University,Knight Foundation School of Computing and Information Sciences,Miami,USA","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123169341","display_name":"Kaida Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaida Wu","raw_affiliation_strings":["Florida International University,Electrical and Computer Engineering,Miami,USA"],"affiliations":[{"raw_affiliation_string":"Florida International University,Electrical and Computer Engineering,Miami,USA","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111337210","display_name":"Peihao Xiang","orcid":"https://orcid.org/0009-0007-4306-111X"},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peihao Xiang","raw_affiliation_strings":["Florida International University,Electrical and Computer Engineering,Miami,USA"],"affiliations":[{"raw_affiliation_string":"Florida International University,Electrical and Computer Engineering,Miami,USA","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085554845","display_name":"Ou Bai","orcid":"https://orcid.org/0000-0002-0040-6807"},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ou Bai","raw_affiliation_strings":["Florida International University,Electrical and Computer Engineering,Miami,USA"],"affiliations":[{"raw_affiliation_string":"Florida International University,Electrical and Computer Engineering,Miami,USA","institution_ids":["https://openalex.org/I19700959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028246785"],"corresponding_institution_ids":["https://openalex.org/I19700959"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8757858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5343000292778015,"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":0.5343000292778015,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.14390000700950623,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.026000000536441803,"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/autoencoder","display_name":"Autoencoder","score":0.8190000057220459},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8180000185966492},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7929999828338623},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6590999960899353},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6155999898910522},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5303000211715698},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5270000100135803}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8190000057220459},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8180000185966492},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7929999828338623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6708999872207642},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6590999960899353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.656499981880188},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6155999898910522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5303999781608582},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.45879998803138733},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3197999894618988},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2890999913215637},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26339998841285706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5504471659660339}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1987971958","https://openalex.org/W2038101708","https://openalex.org/W2113054345","https://openalex.org/W2146334809","https://openalex.org/W2726515241","https://openalex.org/W2753324760","https://openalex.org/W2808631503","https://openalex.org/W2948978827","https://openalex.org/W2962788625","https://openalex.org/W2963470929","https://openalex.org/W2979593053","https://openalex.org/W3012170331","https://openalex.org/W3015241559","https://openalex.org/W3015707499","https://openalex.org/W3024869864","https://openalex.org/W3197103763","https://openalex.org/W3212886388","https://openalex.org/W4205742757","https://openalex.org/W4224925560","https://openalex.org/W4225329057","https://openalex.org/W4280552695","https://openalex.org/W4286747238","https://openalex.org/W4311415873","https://openalex.org/W4377143185","https://openalex.org/W4377227355","https://openalex.org/W4385822773","https://openalex.org/W4385822827","https://openalex.org/W4388233464","https://openalex.org/W4392902630","https://openalex.org/W4396982391","https://openalex.org/W4406858911"],"related_works":[],"abstract_inverted_index":{"Speaker":[0],"clustering":[1,77,92,130],"is":[2,36,134],"the":[3,7,32,65,109],"task":[4],"of":[5,13,67,111],"identifying":[6],"unique":[8],"speakers":[9,28],"in":[10,31,75,117],"a":[11,73,86,94,102],"set":[12],"audio":[14],"recordings":[15],"(each":[16],"belonging":[17],"to":[18,51,72],"exactly":[19],"one":[20],"speaker)":[21],"without":[22],"knowing":[23],"who":[24],"and":[25,70,108,126],"how":[26],"many":[27],"are":[29],"present":[30],"entire":[33],"data,":[34],"which":[35],"essential":[37],"for":[38],"speaker":[39,45,53,68,76,113,124,129],"diarization":[40],"processes.":[41],"Recently,":[42],"off-the-shelf":[43],"deep":[44,112],"embedding":[46],"models":[47],"have":[48],"been":[49],"leveraged":[50],"capture":[52],"characteristics.":[54],"However,":[55],"speeches":[56],"containing":[57],"emotional":[58,106],"expressions":[59],"pose":[60],"significant":[61],"challenges,":[62],"often":[63],"affecting":[64],"accuracy":[66],"embeddings":[69,125],"leading":[71],"decline":[74],"performance.":[78,131],"To":[79],"tackle":[80],"this":[81],"problem,":[82],"we":[83],"propose":[84],"DTG-VAE,":[85],"novel":[87],"disentanglement":[88],"method":[89],"that":[90],"enhances":[91,128],"within":[93],"Variational":[95],"Autoencoder":[96],"(VAE)":[97],"framework.":[98],"This":[99],"study":[100],"reveals":[101],"direct":[103],"link":[104],"between":[105],"states":[107],"effectiveness":[110],"embeddings.":[114],"As":[115],"demonstrated":[116],"our":[118],"experiments,":[119],"DTG-VAE":[120],"extracts":[121],"more":[122],"robust":[123],"significantly":[127],"Our":[132],"code":[133],"available:":[135],"https://github.com/Toby28/DDSESC.":[136]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}