{"id":"https://openalex.org/W4416035864","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.241","title":"Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation","display_name":"Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035864","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.241"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.241","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.241","pdf_url":"https://aclanthology.org/2025.findings-emnlp.241.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.241.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120308929","display_name":"Pengchao Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengchao Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101838736","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-8195-3262"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034677845","display_name":"Wenxi Chen","orcid":"https://orcid.org/0009-0005-8303-930X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695372","display_name":"Yao Li","orcid":"https://orcid.org/0000-0002-1526-2279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662529","display_name":"Sheng Wang","orcid":"https://orcid.org/0000-0003-3385-3109"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie Chen","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":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4499","last_page":"4507"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8521999716758728,"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":0.8521999716758728,"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":0.046799998730421066,"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":0.031300000846385956,"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/set","display_name":"Set (abstract data type)","score":0.29030001163482666},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.27549999952316284},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27459999918937683},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.25130000710487366},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2484000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5641999840736389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3287000060081482},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2484000027179718},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2484000027179718},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2451999932527542},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24390000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.241","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.241","pdf_url":"https://aclanthology.org/2025.findings-emnlp.241.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.241","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.241","pdf_url":"https://aclanthology.org/2025.findings-emnlp.241.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3278014984","display_name":null,"funder_award_id":"U23B2018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035864.pdf","grobid_xml":"https://content.openalex.org/works/W4416035864.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"speech-to-speech":[1],"(S2S)":[2],"dialogue":[3,103],"systems":[4,29,104],"have":[5],"recently":[6],"garnered":[7],"increasing":[8],"research":[9],"attention":[10],"for":[11,126],"their":[12],"lower":[13],"latency":[14],"and":[15,25,62,135],"more":[16],"natural":[17],"integration":[18,69,129],"of":[19,70,100],"nonverbal":[20],"cues":[21],"such":[22],"as":[23],"emotion":[24],"speaker":[26],"identity.However,":[27],"these":[28],"face":[30],"key":[31],"challenges,":[32],"particularly":[33],"in":[34,46,55,130],"incorporating":[35],"external":[36],"knowledge,":[37,65],"a":[38,77,123],"capability":[39],"commonly":[40],"addressed":[41],"by":[42],"Retrieval-Augmented":[43],"Generation":[44],"(RAG)":[45],"text-based":[47],"large":[48],"language":[49],"models":[50],"(LLMs).The":[51],"core":[52],"difficulty":[53],"lies":[54],"the":[56,98,110,116],"modality":[57],"gap":[58],"between":[59],"input":[60],"speech":[61,89],"retrieved":[63],"textual":[64,86],"which":[66],"hinders":[67],"effective":[68],"information.To":[71],"address":[72],"this":[73],"issue,":[74],"we":[75],"propose":[76],"novel":[78],"end-to-end":[79,101,131],"RAG":[80],"framework":[81,121],"that":[82,93],"directly":[83],"retrieves":[84],"relevant":[85],"knowledge":[87,128],"from":[88],"queries.Experimental":[90],"results":[91],"demonstrate":[92],"our":[94,120],"method":[95],"significantly":[96],"improves":[97],"performance":[99,112],"S2S":[102,132],"while":[105],"achieving":[106],"higher":[107],"retrieval":[108],"efficiency.Although":[109],"overall":[111],"still":[113],"lags":[114],"behind":[115],"SOTA":[117],"cascaded":[118],"models,":[119],"offers":[122],"promising":[124],"direction":[125],"enhancing":[127],"systems.Our":[133],"code":[134],"dataset":[136],"are":[137],"released.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}