{"id":"https://openalex.org/W4414772351","doi":"https://doi.org/10.1007/978-3-032-05892-8_1","title":"Development of a Multimodal Dialogue System Integrating Speech Recognition, Knowledge Reasoning, and TTS via Multimodal Large Language Models","display_name":"Development of a Multimodal Dialogue System Integrating Speech Recognition, Knowledge Reasoning, and TTS via Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4414772351","doi":"https://doi.org/10.1007/978-3-032-05892-8_1"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-05892-8_1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-05892-8_1","pdf_url":null,"source":{"id":"https://openalex.org/S4210216571","display_name":"Lecture notes on data engineering and communications technologies","issn_l":"2367-4512","issn":["2367-4512","2367-4520"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes on Data Engineering and Communications Technologies","raw_type":"book-chapter"},"type":"conference-paper","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/A5111291749","display_name":"Zhiyi Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]},{"id":"https://openalex.org/I46305995","display_name":"Taiyuan University of Science and Technology","ror":"https://ror.org/01wcbdc92","country_code":"CN","type":"education","lineage":["https://openalex.org/I46305995"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyi Gao","raw_affiliation_strings":["Shanxi Vocational University of Engineering Science and Technology, Taiyuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanxi Vocational University of Engineering Science and Technology, Taiyuan, China","institution_ids":["https://openalex.org/I181877577","https://openalex.org/I46305995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071380846","display_name":"Akio Doi","orcid":"https://orcid.org/0000-0003-4517-4576"},"institutions":[{"id":"https://openalex.org/I6090238","display_name":"Iwate Prefectural University","ror":"https://ror.org/054dx8336","country_code":"JP","type":"education","lineage":["https://openalex.org/I6090238"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akio Doi","raw_affiliation_strings":["Iwate Prefectural University, Takizawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iwate Prefectural University, Takizawa, Japan","institution_ids":["https://openalex.org/I6090238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113390880","display_name":"Toru Katoh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Toru Katoh","raw_affiliation_strings":["Sapporo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapporo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068330006","display_name":"Meguru Yamashita","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meguru Yamashita","raw_affiliation_strings":["Sapporo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapporo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031349003","display_name":"Hiroki Takahashi","orcid":"https://orcid.org/0000-0001-8370-3243"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroki Takahashi","raw_affiliation_strings":["Sapporo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapporo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111291749"],"corresponding_institution_ids":["https://openalex.org/I181877577","https://openalex.org/I46305995"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2341947,"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":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9653000235557556,"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":0.9653000235557556,"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/speech-technology","display_name":"Speech technology","score":0.49970000982284546},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.4661000072956085},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45509999990463257},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.4408999979496002},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.3937999904155731},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.3675999939441681},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3628000020980835},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.358599990606308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015999794006348},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5131999850273132},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.49970000982284546},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.4661000072956085},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39879998564720154},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3847000002861023},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3813999891281128},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.28529998660087585},{"id":"https://openalex.org/C14919245","wikidata":"https://www.wikidata.org/wiki/Q1976109","display_name":"Language technology","level":4,"score":0.2782999873161316},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2776542497","wikidata":"https://www.wikidata.org/wiki/Q5266672","display_name":"Development (topology)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-05892-8_1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-05892-8_1","pdf_url":null,"source":{"id":"https://openalex.org/S4210216571","display_name":"Lecture notes on data engineering and communications technologies","issn_l":"2367-4512","issn":["2367-4512","2367-4520"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes on Data Engineering and Communications Technologies","raw_type":"book-chapter"}],"best_oa_location":null,"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":null,"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
