{"id":"https://openalex.org/W4415433418","doi":"https://doi.org/10.21437/interspeech.2025-1075","title":"Towards Human-like Multimodal Conversational Agent by Generating Engaging Speech","display_name":"Towards Human-like Multimodal Conversational Agent by Generating Engaging Speech","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433418","doi":"https://doi.org/10.21437/interspeech.2025-1075"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1075","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.14627","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100743703","display_name":"Tae Soo Kim","orcid":"https://orcid.org/0000-0002-0471-9536"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taesoo Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048268638","display_name":"Yong Un Jo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongsik Jo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109452554","display_name":"Hyunmin Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyunmin Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100434365","display_name":"Tae\u2010Hwan Kim","orcid":"https://orcid.org/0000-0002-3542-2276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taehwan Kim","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.260212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4828","last_page":"4832"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9927999973297119,"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":0.9927999973297119,"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/T12128","display_name":"AI in Service Interactions","score":0.948199987411499,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9354000091552734,"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/conversation","display_name":"Conversation","score":0.8458999991416931},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.6944000124931335},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.6208000183105469},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.61080002784729},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5375000238418579},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.5335000157356262},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.4487999975681305},{"id":"https://openalex.org/keywords/mood","display_name":"Mood","score":0.3921000063419342}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8458999991416931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7055000066757202},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.6944000124931335},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.6208000183105469},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.61080002784729},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.5335000157356262},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5138999819755554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4575999975204468},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44110000133514404},{"id":"https://openalex.org/C2780733359","wikidata":"https://www.wikidata.org/wiki/Q331769","display_name":"Mood","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.35109999775886536},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.30869999527931213},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30559998750686646},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.28139999508857727},{"id":"https://openalex.org/C2780829048","wikidata":"https://www.wikidata.org/wiki/Q1624720","display_name":"Conversation analysis","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1075","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.14627","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.14627","pdf_url":"https://arxiv.org/pdf/2509.14627","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,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.14627","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.14627","pdf_url":"https://arxiv.org/pdf/2509.14627","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,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Human":[0],"conversation":[1,61,123],"involves":[2],"language,":[3],"speech,":[4],"and":[5,47,63,98,119],"visual":[6,118],"cues,":[7],"with":[8],"each":[9],"medium":[10],"providing":[11],"complementary":[12],"information.":[13,66,109],"For":[14],"instance,":[15],"speech":[16,57,79,106],"conveys":[17],"a":[18,52,72,90],"vibe":[19],"or":[20],"tone":[21],"not":[22],"fully":[23],"captured":[24],"by":[25],"text":[26,34,96],"alone.":[27],"While":[28],"multimodal":[29,91],"LLMs":[30],"focus":[31],"on":[32,60,78],"generating":[33,45,95],"responses":[35,58,97],"from":[36],"diverse":[37],"inputs,":[38],"less":[39],"attention":[40],"has":[41],"been":[42],"paid":[43],"to":[44,80,83,104,124],"natural":[46,85],"engaging":[48,126],"speech.":[49,86,127],"We":[50,87],"propose":[51,89],"human-like":[53],"agent":[54],"that":[55],"generates":[56],"based":[59],"mood":[62],"responsive":[64],"style":[65],"To":[67],"achieve":[68],"this,":[69],"we":[70],"build":[71],"novel":[73],"MultiSensory":[74],"Conversation":[75],"dataset":[76],"focused":[77],"enable":[81],"agents":[82],"generate":[84,105,125],"then":[88],"LLM-based":[92],"model":[93],"for":[94],"voice":[99],"descriptions,":[100],"which":[101],"are":[102],"used":[103],"covering":[107],"paralinguistic":[108],"Experimental":[110],"results":[111],"demonstrate":[112],"the":[113],"effectiveness":[114],"of":[115],"utilizing":[116],"both":[117],"audio":[120],"modalities":[121],"in":[122,133],"The":[128],"source":[129],"code":[130],"is":[131],"available":[132],"https://github.com/kimtaesu24/MSenC":[134]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-23T00:00:00"}