{"id":"https://openalex.org/W4415275357","doi":"https://doi.org/10.18653/v1/2026.findings-acl.26","title":"Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses","display_name":"Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415275357","doi":"https://doi.org/10.18653/v1/2026.findings-acl.26"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.26","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.26","pdf_url":"https://aclanthology.org/2026.findings-acl.26.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.26.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048886717","display_name":"Sungnyun Kim","orcid":"https://orcid.org/0000-0002-3251-1812"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungnyun Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082991654","display_name":"Kangwook Jang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kangwook Jang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021338398","display_name":"Sung\u2010Woo Cho","orcid":"https://orcid.org/0000-0003-0827-4471"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungwoo Cho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066573438","display_name":"Hoirin Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoi-Rin Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091674853","display_name":"Se-Young Yun","orcid":"https://orcid.org/0000-0001-6675-5113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Se-Young Yun","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02629048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"544","last_page":"564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9222999811172485,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9107999801635742,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/word-error-rate","display_name":"Word error rate","score":0.6383000016212463},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6123999953269958},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5235000252723694},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.489300012588501},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47859999537467957},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4438000023365021},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4251999855041504},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3763999938964844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829999923706055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7059999704360962},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6383000016212463},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6123999953269958},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5235000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4918999969959259},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.489300012588501},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4251999855041504},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39079999923706055},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3763999938964844},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.33709999918937683},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26669999957084656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.26","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.26","pdf_url":"https://aclanthology.org/2026.findings-acl.26.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: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.13281","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.13281","pdf_url":"https://arxiv.org/pdf/2510.13281","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.13281","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.13281","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.26","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.26","pdf_url":"https://aclanthology.org/2026.findings-acl.26.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4021044050","display_name":null,"funder_award_id":"2022-0-00641","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5204723964","display_name":null,"funder_award_id":"2022-0-00641","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415275357.pdf","grobid_xml":"https://content.openalex.org/works/W4415275357.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,30,62],"new":[4],"paradigm":[5],"for":[6,94],"generative":[7],"error":[8,107],"correction":[9],"(GER)":[10],"framework":[11,102],"in":[12,23],"audio-visual":[13],"speech":[14,44,49],"recognition":[15,45,50],"(AVSR)":[16],"that":[17,66,123],"reasons":[18],"over":[19,114],"modality-specific":[20],"evidences":[21],"directly":[22],"the":[24,54,71,74,82,111,136,139],"language":[25,32],"space.Our":[26],"framework,":[27,133],"DualHyp,":[28,57],"empowers":[29],"large":[31],"model":[33,83],"(LLM)":[34],"to":[35,70,84,105,119],"compose":[36],"independent":[37],"N":[38],"-best":[39],"hypotheses":[40,93,145],"from":[41],"separate":[42],"automatic":[43],"(ASR)":[46],"and":[47,91,138,143],"visual":[48],"(VSR)":[51],"models.To":[52],"maximize":[53],"effectiveness":[55],"of":[56,77],"we":[58,134],"further":[59],"introduce":[60],"Rel-Prompt,":[61],"noise-aware":[63],"guidance":[64],"mechanism":[65],"provides":[67],"modality-grounded":[68],"prompts":[69],"LLM.RelPrompt":[72],"offers":[73],"temporal":[75],"reliability":[76],"each":[78],"modality":[79],"stream,":[80],"guiding":[81],"dynamically":[85],"switch":[86],"its":[87],"focus":[88],"between":[89],"ASR":[90,116,142],"VSR":[92,144],"an":[95],"accurate":[96],"correction.Under":[97],"various":[98],"corruption":[99],"scenarios,":[100],"our":[101,131],"attains":[103],"up":[104],"57.7%":[106],"rate":[108],"gain":[109],"on":[110],"LRS2":[112],"benchmark":[113],"standard":[115],"baseline,":[117],"contrary":[118],"single-stream":[120],"GER":[121],"approaches":[122],"achieve":[124],"only":[125],"10%":[126],"gain.To":[127],"facilitate":[128],"research":[129],"within":[130],"DualHyp":[132],"release":[135],"code":[137],"dataset":[140],"comprising":[141],"at":[146],"https:":[147],"//github.com/sungnyun/dualhyp.":[148]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-17T00:00:00"}