{"id":"https://openalex.org/W4408354137","doi":"https://doi.org/10.1109/icassp49660.2025.10888680","title":"SLIDE: Integrating Speech Language Model with LLM for Spontaneous Spoken Dialogue Generation","display_name":"SLIDE: Integrating Speech Language Model with LLM for Spontaneous Spoken Dialogue Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354137","doi":"https://doi.org/10.1109/icassp49660.2025.10888680"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"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/A5017349618","display_name":"Haitian Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitian Lu","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072887461","display_name":"Gaofeng Cheng","orcid":"https://orcid.org/0000-0002-2102-6061"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaofeng Cheng","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100569047","display_name":"Liuping Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114441","display_name":"Zhejiang Provincial Public Security Department","ror":"https://ror.org/01z3tch16","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210114441"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liuping Luo","raw_affiliation_strings":["Guangdong Provincial,Public Security Department,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial,Public Security Department,Guangzhou,China","institution_ids":["https://openalex.org/I4210114441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675228","display_name":"Leying Zhang","orcid":"https://orcid.org/0009-0008-1424-9604"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leying Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,AudioCC Lab, MoE Key Lab of AI,CS Dept,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,AudioCC Lab, MoE Key Lab of AI,CS Dept,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,AudioCC Lab, MoE Key Lab of AI,CS Dept,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,AudioCC Lab, MoE Key Lab of AI,CS Dept,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036446253","display_name":"Pengyuan Zhang","orcid":"https://orcid.org/0000-0001-6838-5160"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyuan Zhang","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9878000020980835,"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":0.9878000020980835,"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":0.9695000052452087,"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/T10028","display_name":"Topic Modeling","score":0.9587000012397766,"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/computer-science","display_name":"Computer science","score":0.7964079976081848},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.576806902885437},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5650948286056519},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5243765711784363},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48442962765693665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3648235499858856},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32175466418266296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964079976081848},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.576806902885437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5650948286056519},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5243765711784363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48442962765693665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3648235499858856},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32175466418266296},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W175385064","https://openalex.org/W1986450839","https://openalex.org/W2001292406","https://openalex.org/W2747874407","https://openalex.org/W2962904995","https://openalex.org/W3016191377","https://openalex.org/W3140429000","https://openalex.org/W3161207330","https://openalex.org/W3209059054","https://openalex.org/W4285203343","https://openalex.org/W4296094953","https://openalex.org/W4307680525","https://openalex.org/W4381786045","https://openalex.org/W4385822353","https://openalex.org/W4385822356","https://openalex.org/W4390224291","https://openalex.org/W4391021755","https://openalex.org/W4392909068","https://openalex.org/W4396877837","https://openalex.org/W4402167588","https://openalex.org/W4403863362","https://openalex.org/W6603931906","https://openalex.org/W6739901393","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6787253756","https://openalex.org/W6790356757","https://openalex.org/W6847363464","https://openalex.org/W6853998256","https://openalex.org/W6857084855","https://openalex.org/W6864493879"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2388125677","https://openalex.org/W2159057708","https://openalex.org/W405926467","https://openalex.org/W2252095989","https://openalex.org/W4402742086","https://openalex.org/W1965611333","https://openalex.org/W2906185611","https://openalex.org/W4404882811","https://openalex.org/W633922780"],"abstract_inverted_index":{"Recently,":[0],"\"textless\"":[1],"speech":[2,8,24],"language":[3],"models":[4],"(SLMs)":[5],"based":[6],"on":[7,86,100],"units":[9],"have":[10],"made":[11],"huge":[12],"progress":[13],"in":[14],"generating":[15],"naturalistic":[16,110],"speech,":[17],"including":[18],"non-verbal":[19],"vocalizations.":[20],"However,":[21],"the":[22,53,62,77,87,95,101],"generated":[23],"samples":[25],"often":[26],"lack":[27],"semantic":[28,116],"coherence.":[29,117],"In":[30],"this":[31],"paper,":[32],"we":[33,46,60],"propose":[34],"SLM":[35,84],"and":[36,68],"LLM":[37,50],"Integration":[38],"for":[39],"spontaneous":[40],"spoken":[41,57,88,111],"Dialogue":[42],"gEneration":[43],"(SLIDE).":[44],"Specifically,":[45],"first":[47],"utilize":[48],"an":[49,83],"to":[51,75,93],"generate":[52,109],"textual":[54,63,96],"content":[55],"of":[56,79],"dialogue.":[58,97],"Next,":[59],"convert":[61],"dialogues":[64],"into":[65],"phoneme":[66,89],"sequences":[67,90],"use":[69],"a":[70],"two-tower":[71],"transformer-based":[72],"duration":[73,78],"predictor":[74],"predict":[76],"each":[80],"phoneme.":[81],"Finally,":[82],"conditioned":[85],"is":[91],"used":[92],"vocalize":[94],"Experimental":[98],"results":[99],"Fisher":[102],"dataset":[103],"demonstrate":[104],"that":[105],"our":[106],"system":[107],"can":[108],"dialogue":[112],"while":[113],"maintaining":[114],"high":[115]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}