{"id":"https://openalex.org/W7166845043","doi":"https://doi.org/10.18653/v1/2026.acl-long.1428","title":"SpeechMedAssist: Efficiently and Effectively Adapting Speech Language Models for Medical Consultation","display_name":"SpeechMedAssist: Efficiently and Effectively Adapting Speech Language Models for Medical Consultation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166845043","doi":"https://doi.org/10.18653/v1/2026.acl-long.1428"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1428","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1428","pdf_url":"https://aclanthology.org/2026.acl-long.1428.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 64th 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/2026.acl-long.1428.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102673309","display_name":"Sirry Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210105561","display_name":"Institute for Management of Innovation and Technology","ror":"https://ror.org/01cnprv20","country_code":"SE","type":"facility","lineage":["https://openalex.org/I4210105561"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Sirry Chen","raw_affiliation_strings":["Fudan University","Shanghai Innovation Institude"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Innovation Institude","institution_ids":["https://openalex.org/I4210105561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139775892","display_name":"Jieyi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieyi Wang","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139771840","display_name":"Wei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Fudan University","Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139791679","display_name":"Zhongyu Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210105561","display_name":"Institute for Management of Innovation and Technology","ror":"https://ror.org/01cnprv20","country_code":"SE","type":"facility","lineage":["https://openalex.org/I4210105561"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Zhongyu Wei","raw_affiliation_strings":["Fudan University","Shanghai Innovation Institude"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Innovation Institude","institution_ids":["https://openalex.org/I4210105561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81248047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"30914","last_page":"30935"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.6506999731063843,"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":0.6506999731063843,"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":0.041600000113248825,"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":0.03629999980330467,"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/language-model","display_name":"Language model","score":0.37470000982284546},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.35580000281333923},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.2815999984741211},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.25760000944137573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6165000200271606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44510000944137573},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36079999804496765},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3481999933719635},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3163999915122986},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2547999918460846},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1428","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1428","pdf_url":"https://aclanthology.org/2026.acl-long.1428.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1428","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1428","pdf_url":"https://aclanthology.org/2026.acl-long.1428.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321851","display_name":"Fudan University","ror":"https://ror.org/013q1eq08"},{"id":"https://openalex.org/F4320325413","display_name":"Shanghai Municipal Commission of Economy and Informatization","ror":"https://ror.org/04166ws88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166845043.pdf","grobid_xml":"https://content.openalex.org/works/W7166845043.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Medical":[0],"consultations":[1],"are":[2,13],"intrinsically":[3],"speechcentric.However,":[4],"most":[5,149],"prior":[6],"works":[7],"focus":[8],"on":[9,42],"long-text-based":[10],"interactions,":[11],"which":[12],"cumbersome":[14],"and":[15,36,95,131,146],"patient-unfriendly.Recent":[16],"advances":[17],"in":[18,51,143,148],"speech":[19,34,43,109],"language":[20],"models":[21],"(SpeechLMs)":[22],"have":[23],"enabled":[24],"more":[25],"natural":[26],"speech-based":[27,65],"interaction,":[28],"yet":[29],"the":[30,37,47,71,78,105],"scarcity":[31],"of":[32,39,49,63,74,87],"medical":[33,52,108,119],"data":[35,44,110],"inefficiency":[38],"directly":[40],"fine-tuning":[41],"jointly":[45],"hinder":[46],"adoption":[48],"SpeechLMs":[50,117],"consultation.In":[53],"this":[54],"paper,":[55],"we":[56,76,122],"propose":[57],"SpeechMedAssist,":[58],"a":[59,83,124],"SpeechLM":[60],"natively":[61],"capable":[62],"conducting":[64],"multi-turn":[66,132],"interactions":[67],"with":[68,99],"patients.By":[69],"exploiting":[70],"architectural":[72],"properties":[73],"SpeechLMs,":[75],"decouple":[77],"conventional":[79],"one-stage":[80],"training":[81],"into":[82],"two-stage":[84],"paradigm":[85],"consisting":[86],"(1)":[88],"Knowledge":[89],"&":[90],"Capability":[91],"Injection":[92],"via":[93],"Text":[94],"(2)":[96],"Modality":[97],"Re-alignment":[98],"Limited":[100],"Speech":[101],"Data,":[102],"thereby":[103],"reducing":[104],"requirement":[106],"for":[107,118],"to":[111],"only":[112],"10k":[113],"synthesized":[114],"samples.To":[115],"evaluate":[116],"consultation":[120],"scenarios,":[121],"design":[123],"benchmark":[125],"comprising":[126],"both":[127,144],"single-turn":[128],"question":[129],"answering":[130],"simulated":[133],"interactions.Experimental":[134],"results":[135],"show":[136],"that":[137],"our":[138],"model":[139],"outperforms":[140],"all":[141],"baselines":[142],"effectiveness":[145],"robustness":[147],"evaluation":[150],"settings.":[151],"1":[152]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-07-02T00:00:00"}