{"id":"https://openalex.org/W4416307833","doi":"https://doi.org/10.18653/v1/2026.acl-long.1954","title":"AV-Dialog: Spoken Dialogue Models with Audio-Visual Input","display_name":"AV-Dialog: Spoken Dialogue Models with Audio-Visual Input","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416307833","doi":"https://doi.org/10.18653/v1/2026.acl-long.1954"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1954","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1954","pdf_url":null,"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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/2026.acl-long.1954","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091414943","display_name":"Tuochao Chen","orcid":"https://orcid.org/0000-0002-8031-5066"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuochao Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080881573","display_name":"Bandhav Veluri","orcid":"https://orcid.org/0000-0002-5086-9092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bandhav Veluri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103000746","display_name":"Hongyu Gong","orcid":"https://orcid.org/0000-0002-7071-0070"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyu Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011077730","display_name":"Shyamnath Gollakota","orcid":"https://orcid.org/0000-0002-9863-3054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shyamnath Gollakota","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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01999531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42208","last_page":"42225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8683000206947327,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8683000206947327,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.059700001031160355,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.019200000911951065,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.5684000253677368},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5447999835014343},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4291999936103821},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.35339999198913574},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.34119999408721924},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3359000086784363},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.32010000944137573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976999878883362},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5684000253677368},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5605000257492065},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5303000211715698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5110999941825867},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.34119999408721924},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1954","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1954","pdf_url":null,"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"},{"id":"pmh:oai:arXiv.org:2511.11124","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.11124","pdf_url":"https://arxiv.org/pdf/2511.11124","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.11124","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.11124","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.acl-long.1954","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1954","pdf_url":null,"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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dialogue":[0],"models":[1,80],"falter":[2],"in":[3,69,118],"noisy,":[4],"multi-speaker":[5],"environments,":[6],"often":[7],"producing":[8],"irrelevant":[9],"responses":[10],"and":[11,26,36,51,65,89],"awkward":[12],"turn-taking.":[13],"We":[14],"present":[15],"AV-Dialog,":[16],"the":[17,31,97,109],"first":[18],"multimodal":[19],"dialog":[20],"framework":[21],"that":[22,76,115],"uses":[23],"both":[24],"audio":[25],"visual":[27],"cues":[28],"to":[29],"track":[30],"target":[32],"speaker,":[33],"predict":[34],"turn-taking,":[35],"generate":[37],"coherent":[38],"responses.":[39],"By":[40],"combining":[41],"acoustic":[42],"tokenization":[43],"with":[44],"multi-task,":[45],"multi-stage":[46],"training":[47],"on":[48],"monadic,":[49],"synthetic,":[50],"real":[52],"audio-visual":[53],"dialogue":[54,92,113],"datasets,":[55],"AV-Dialog":[56,77],"achieves":[57],"robust":[58],"streaming":[59],"transcription,":[60],"semantically":[61],"grounded":[62],"turn-boundary":[63],"detection":[64],"accurate":[66],"responses,":[67],"resulting":[68],"a":[70],"natural":[71],"conversational":[72],"flow.":[73],"Experiments":[74],"show":[75],"outperforms":[78],"audio-only":[79],"under":[81],"interference,":[82],"reducing":[83],"transcription":[84],"errors,":[85],"improving":[86],"turn-taking":[87],"prediction,":[88],"enhancing":[90],"human-rated":[91],"quality.":[93],"These":[94],"results":[95],"highlight":[96],"power":[98],"of":[99],"seeing":[100],"as":[101,103],"well":[102],"hearing":[104],"for":[105,111],"speaker-aware":[106],"interaction,":[107],"paving":[108],"way":[110],"{spoken}":[112],"agents":[114],"perform":[116],"{robustly}":[117],"real-world,":[119],"noisy":[120],"environments.":[121]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-11-18T00:00:00"}