{"id":"https://openalex.org/W4416799017","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249248","title":"Improving Listening Head Generation Performance Using Speech Representations from Self-Supervised Learning","display_name":"Improving Listening Head Generation Performance Using Speech Representations from Self-Supervised Learning","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799017","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249248"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5120619706","display_name":"Tamon Mikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tamon Mikawa","raw_affiliation_strings":["Toyohashi University of Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyohashi University of Technology,Japan","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102171465","display_name":"Yasuhisa Fujii","orcid":null},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuhisa Fujii","raw_affiliation_strings":["Toyohashi University of Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyohashi University of Technology,Japan","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103010851","display_name":"Yukoh Wakabayashi","orcid":"https://orcid.org/0000-0001-8846-3699"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yukoh Wakabayashi","raw_affiliation_strings":["Google DeepMind,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,Japan","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090927220","display_name":"Kengo Ohta","orcid":null},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kengo Ohta","raw_affiliation_strings":["Toyohashi University of Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyohashi University of Technology,Japan","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024519127","display_name":"Ryota Nishimura","orcid":"https://orcid.org/0000-0002-2948-530X"},"institutions":[{"id":"https://openalex.org/I4210092186","display_name":"Anan National College of Technology","ror":"https://ror.org/01bb68v37","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210092186"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryota Nishimura","raw_affiliation_strings":["National Institute of Technology, Anan College,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology, Anan College,Japan","institution_ids":["https://openalex.org/I4210092186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077234015","display_name":"Norihide Kitaoka","orcid":"https://orcid.org/0000-0003-2028-8585"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norihide Kitaoka","raw_affiliation_strings":["Toyohashi University of Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyohashi University of Technology,Japan","institution_ids":["https://openalex.org/I136259955"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34695265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"956","last_page":"961"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.46000000834465027,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.46000000834465027,"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/T12031","display_name":"Speech and dialogue systems","score":0.2004999965429306,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0778999999165535,"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/active-listening","display_name":"Active listening","score":0.7002000212669373},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6082000136375427},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5837000012397766},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5440000295639038},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.5375000238418579},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4498000144958496},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.41179999709129333}],"concepts":[{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.7002000212669373},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6728000044822693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6624000072479248},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6082000136375427},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5837000012397766},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5440000295639038},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41620001196861267},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.41179999709129333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34929999709129333},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C2986659363","wikidata":"https://www.wikidata.org/wiki/Q6646450","display_name":"Listening comprehension","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.29899999499320984},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.29179999232292175},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W126830630","https://openalex.org/W1488075209","https://openalex.org/W2016589492","https://openalex.org/W2118004237","https://openalex.org/W2168982238","https://openalex.org/W2235920218","https://openalex.org/W2295421726","https://openalex.org/W2403714865","https://openalex.org/W2738406145","https://openalex.org/W2747308422","https://openalex.org/W2979894294","https://openalex.org/W3089455867","https://openalex.org/W3108715150","https://openalex.org/W4225760288","https://openalex.org/W4312309978","https://openalex.org/W4312820606","https://openalex.org/W4319862652","https://openalex.org/W4385245566","https://openalex.org/W4408354517"],"related_works":[],"abstract_inverted_index":{"Appropriate,":[0],"non-verbal":[1,25],"listener":[2,49],"behavior":[3],"during":[4],"conversation":[5],"plays":[6],"an":[7],"important":[8,135],"role":[9],"in":[10,29,52],"encouraging":[11],"additional":[12],"speaker":[13],"utterances":[14],"and":[15,35,60,81,100,127],"achieving":[16],"smooth":[17],"turn-taking.":[18],"In":[19],"particular,":[20],"head":[21,50,61],"movements":[22,51],"are":[23],"valuable,":[24],"cues":[26],"frequently":[27],"used":[28],"response":[30],"to":[31],"the":[32,41,57,70,128,142],"speaker's":[33,58],"speech":[34,93,110],"movements.":[36,62],"This":[37],"study":[38,105],"focuses":[39],"on":[40],"Listening":[42],"Head":[43],"Generation":[44],"(LHG)":[45],"task,":[46],"which":[47],"generates":[48],"automated":[53],"dialogue":[54,148],"systems":[55],"from":[56,113],"voice":[59],"Through":[63],"a":[64],"performance":[65],"comparison":[66],"experiment,":[67],"we":[68],"verify":[69],"effectiveness":[71],"of":[72,144],"self-supervised":[73],"learning":[74],"(SSL)":[75],"models,":[76],"such":[77,95,120],"as":[78,96,121],"Wav2Vec":[79],"2.0":[80],"HuBERT,":[82],"for":[83,141],"LHG":[84,88],"tasks.":[85],"While":[86],"conventional":[87],"methods":[89],"have":[90],"employed":[91],"traditional":[92],"features":[94],"log-Mel":[97],"filter":[98],"bank":[99],"Mel-frequency":[101],"cepstral":[102],"coefficients,":[103],"this":[104],"confirms":[106],"that":[107,137],"utilizing":[108],"latent":[109],"representations":[111],"acquired":[112],"SSL":[114],"models":[115],"improves":[116],"objective":[117],"evaluation":[118],"metrics":[119],"<tex":[122],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[123],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{L":[124],"2}$</tex>":[125],"error":[126],"Pearson":[129],"Correlation":[130],"Coefficient.":[131],"Our":[132],"results":[133],"provide":[134],"insights":[136],"will":[138],"be":[139],"useful":[140],"realization":[143],"completely":[145],"bidirectional":[146],"multimodal":[147],"systems.":[149]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}