{"id":"https://openalex.org/W4405709767","doi":"https://doi.org/10.1109/iscslp63861.2024.10800066","title":"Inferring Agent Speaking Styles for Auditory-Visual User-Agent Conversation","display_name":"Inferring Agent Speaking Styles for Auditory-Visual User-Agent Conversation","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709767","doi":"https://doi.org/10.1109/iscslp63861.2024.10800066"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5024368167","display_name":"Zhihan Yang","orcid":"https://orcid.org/0009-0004-1659-1404"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihan Yang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100601921","display_name":"Chunfeng Wang","orcid":"https://orcid.org/0000-0001-9949-7528"},"institutions":[{"id":"https://openalex.org/I4210126929","display_name":"CE Technologies (United Kingdom)","ror":"https://ror.org/02pw67e25","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210126929"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chunfeng Wang","raw_affiliation_strings":["Bytedance Inc,Beijing"],"affiliations":[{"raw_affiliation_string":"Bytedance Inc,Beijing","institution_ids":["https://openalex.org/I4210126929"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667025","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0002-6527-5502"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039477812","display_name":"Jia Jia","orcid":"https://orcid.org/0009-0005-8449-278X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024368167"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21969801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"421","last_page":"425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9480000138282776,"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/T12031","display_name":"Speech and dialogue systems","score":0.9480000138282776,"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/T12290","display_name":"Human Motion and Animation","score":0.9333000183105469,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.8662877082824707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7635403871536255},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5632862448692322},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.4696459174156189},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4331710934638977},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33688920736312866},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.234920471906662},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.23267433047294617},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2021481692790985}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8662877082824707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635403871536255},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5632862448692322},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.4696459174156189},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4331710934638977},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33688920736312866},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.234920471906662},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.23267433047294617},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2021481692790985},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2022068631","https://openalex.org/W2091550557","https://openalex.org/W2146334809","https://openalex.org/W3197824033","https://openalex.org/W4225300652","https://openalex.org/W4297841448","https://openalex.org/W4304013787","https://openalex.org/W4312337341","https://openalex.org/W4372260474","https://openalex.org/W4375868859","https://openalex.org/W4387968649","https://openalex.org/W6755207826","https://openalex.org/W6778823374","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W1968552888","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W1511346092","https://openalex.org/W3156017614","https://openalex.org/W2742181818","https://openalex.org/W2612412344","https://openalex.org/W2053633997","https://openalex.org/W337810568"],"abstract_inverted_index":{"Conversational":[0],"text-to-speech":[1],"(TTS)":[2],"aims":[3],"to":[4,19,81,88],"generate":[5],"speech":[6,60,122],"with":[7,61,124],"proper":[8],"style":[9,118],"and":[10,36,64,72,78,120],"emotion":[11,37],"following":[12],"the":[13,20,56,89,111,115],"history":[14],"of":[15,22,58,91],"current":[16],"dialogue":[17],"catering":[18],"demand":[21],"users.":[23],"Meanwhile,":[24],"human":[25],"facial":[26,44],"expression":[27],"is":[28],"a":[29,70,99],"significant":[30],"signal":[31],"in":[32,46,52,84,117],"conversation":[33,125],"for":[34,50,66,105],"intention":[35],"estimation.":[38],"In":[39],"this":[40,106],"paper,":[41],"we":[42,97],"introduce":[43],"expressions":[45],"inferring":[47],"speaking":[48],"styles":[49,63,83],"agents":[51],"TTS":[53],"applications,":[54],"addressing":[55],"challenge":[57],"synthesizing":[59],"appropriate":[62],"emotions":[65],"conversation.":[67],"We":[68],"propose":[69],"multi-modal":[71],"multi-scale":[73],"Transformer":[74],"model":[75],"utilizing":[76],"visual":[77],"auditory":[79],"features":[80],"infer":[82],"synthesized":[85],"speech.":[86],"Due":[87],"insufficiency":[90],"publicly":[92],"available":[93],"visual-auditory":[94],"conversational":[95],"corpora,":[96],"establish":[98],"large-scale,":[100],"high-quality":[101],"multimodal":[102],"dataset,":[103],"Podcast,":[104],"purpose.":[107],"Experimental":[108],"results":[109],"demonstrate":[110],"proposed":[112],"method":[113],"outperforms":[114],"state-of-the-art":[116],"inference":[119],"synthesizes":[121],"coherent":[123],"history.":[126]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
