{"id":"https://openalex.org/W4412945327","doi":"https://doi.org/10.18653/v1/2025.acl-long.613","title":"WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models","display_name":"WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945327","doi":"https://doi.org/10.18653/v1/2025.acl-long.613"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.613","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.613","pdf_url":"https://aclanthology.org/2025.acl-long.613.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.613.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072936428","display_name":"Y.W. Chen","orcid":"https://orcid.org/0000-0003-2566-018X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102904447","display_name":"Shengpeng Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengpeng Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057219846","display_name":"Haoxiao Wang","orcid":"https://orcid.org/0009-0000-4252-4353"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoxiao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033874080","display_name":"Ziqing Wang","orcid":"https://orcid.org/0000-0001-8791-0805"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziqing Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325176","display_name":"Siyu Chen","orcid":"https://orcid.org/0000-0002-6271-1858"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siyu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043581249","display_name":"Jinzheng He","orcid":"https://orcid.org/0009-0003-3024-9624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinzheng He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043896172","display_name":"Jin Xu","orcid":"https://orcid.org/0000-0003-2132-8825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Zhao","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":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12505","last_page":"12523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9919000267982483,"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":0.9689000248908997,"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":0.8150919675827026},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4663863182067871},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44715946912765503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4106357991695404},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3587983250617981}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8150919675827026},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4663863182067871},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44715946912765503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4106357991695404},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3587983250617981}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.613","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.613","pdf_url":"https://aclanthology.org/2025.acl-long.613.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.613","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.613","pdf_url":"https://aclanthology.org/2025.acl-long.613.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1101031052","display_name":null,"funder_award_id":"U24A20326","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945327.pdf","grobid_xml":"https://content.openalex.org/works/W4412945327.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Yifu":[0],"Chen,":[1,9],"Shengpeng":[2],"Ji,":[3],"Haoxiao":[4],"Wang,":[5,7],"Ziqing":[6],"Siyu":[8],"Jinzheng":[10],"He,":[11],"Jin":[12],"Xu,":[13],"Zhou":[14],"Zhao.":[15],"Proceedings":[16],"of":[17,22],"the":[18,23],"63rd":[19],"Annual":[20],"Meeting":[21],"Association":[24],"for":[25],"Computational":[26],"Linguistics":[27],"(Volume":[28],"1:":[29],"Long":[30],"Papers).":[31],"2025.":[32]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
