{"id":"https://openalex.org/W7202200253","doi":"https://doi.org/10.1145/3776574.3831133","title":"From Speech to Interaction: Analyzing Multimodal Systems in Cocktail-Party Scenarios","display_name":"From Speech to Interaction: Analyzing Multimodal Systems in Cocktail-Party Scenarios","publication_year":2026,"publication_date":"2026-10-02","ids":{"openalex":"https://openalex.org/W7202200253","doi":"https://doi.org/10.1145/3776574.3831133"},"language":"en","primary_location":{"id":"doi:10.1145/3776574.3831133","doi":"https://doi.org/10.1145/3776574.3831133","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3776574.3831133","pdf_url":null,"source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 28th International Conference On Multimodal Interaction","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3776574.3831133","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044152577","display_name":"Thai Binh Nguyen","orcid":"https://orcid.org/0009-0008-8100-6338","observed_orcids":["https://orcid.org/0009-0008-8100-6338"]},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thai Binh Nguyen","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0009-0008-8100-6338","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122747789","display_name":"Zhaolin Li","orcid":"https://orcid.org/0000-0001-7433-0115","observed_orcids":["https://orcid.org/0000-0001-7433-0115"]},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zhaolin Li","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7433-0115","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046084081","display_name":"Jan Niehues","orcid":"https://orcid.org/0000-0002-4231-6543","observed_orcids":["https://orcid.org/0000-0002-4231-6543"]},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Niehues","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4231-6543","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023053982","display_name":"Alexander H. Waibel","orcid":"https://orcid.org/0009-0001-0848-1000","observed_orcids":["https://orcid.org/0009-0001-0848-1000"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Waibel","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"raw_orcid":"https://orcid.org/0009-0001-0848-1000","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"223","last_page":"232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6025000214576721,"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":0.6025000214576721,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.3903999924659729,"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/T12031","display_name":"Speech and dialogue systems","score":0.003800000064074993,"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/cocktail-party-problem","display_name":"cocktail party problem","score":0.8730000257492065},{"id":"https://openalex.org/keywords/audio-visual-speech-recognition","display_name":"audio-visual speech recognition","score":0.8230000138282776},{"id":"https://openalex.org/keywords/speaker-separation","display_name":"speaker separation","score":0.4659999907016754},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6669999957084656},{"id":"https://openalex.org/keywords/overlapping-speech","display_name":"overlapping speech","score":0.6940000057220459},{"id":"https://openalex.org/keywords/multimodal-systems","display_name":"multimodal systems","score":0.5410000085830688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76419997215271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6341999769210815},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.611299991607666},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.607200026512146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4765999913215637},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3797000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37959998846054077},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3467000126838684},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3156999945640564},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.2761000096797943},{"id":"https://openalex.org/C541956065","wikidata":"https://www.wikidata.org/wiki/Q2250680","display_name":"Speech error","level":3,"score":0.2750000059604645},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3776574.3831133","doi":"https://doi.org/10.1145/3776574.3831133","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3776574.3831133","pdf_url":null,"source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 28th International Conference On Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.08510","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.08510","pdf_url":"https://arxiv.org/pdf/2608.08510","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,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.08510","doi":"https://doi.org/10.48550/arxiv.2608.08510","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.08510","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5445/ir/1000199042","doi":"https://doi.org/10.5445/ir/1000199042","is_oa":true,"landing_page_url":"https://doi.org/10.5445/ir/1000199042","pdf_url":null,"source":{"id":"https://openalex.org/S7407052948","display_name":"KITopen","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1145/3776574.3831133","doi":"https://doi.org/10.1145/3776574.3831133","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3776574.3831133","pdf_url":null,"source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 28th International Conference On Multimodal Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202200253.pdf","grobid_xml":"https://content.openalex.org/works/W7202200253.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W124086577","https://openalex.org/W1550575505","https://openalex.org/W1552594198","https://openalex.org/W1904457459","https://openalex.org/W1970320256","https://openalex.org/W1993704986","https://openalex.org/W2000221426","https://openalex.org/W2058107683","https://openalex.org/W2078298881","https://openalex.org/W2083751884","https://openalex.org/W2114528521","https://openalex.org/W2136451251","https://openalex.org/W2157023096","https://openalex.org/W2168824259","https://openalex.org/W2169264834","https://openalex.org/W2316138215","https://openalex.org/W2508092598","https://openalex.org/W2551572271","https://openalex.org/W2766219058","https://openalex.org/W2891205112","https://openalex.org/W2970185413","https://openalex.org/W3097777922","https://openalex.org/W3168662520","https://openalex.org/W3177271673","https://openalex.org/W3182657421","https://openalex.org/W3196777808","https://openalex.org/W4289665794","https://openalex.org/W4297841387","https://openalex.org/W4297841641","https://openalex.org/W4297841834","https://openalex.org/W4312443924","https://openalex.org/W4372317224","https://openalex.org/W4372346152","https://openalex.org/W4385822729","https://openalex.org/W4386075783","https://openalex.org/W4391021542","https://openalex.org/W4391021590","https://openalex.org/W4392901809","https://openalex.org/W4392903321","https://openalex.org/W4392931031","https://openalex.org/W4401597516","https://openalex.org/W4402112360","https://openalex.org/W4403640425","https://openalex.org/W4405655184","https://openalex.org/W4406208517","https://openalex.org/W4407186270","https://openalex.org/W4412944939","https://openalex.org/W4414281281","https://openalex.org/W4414939355","https://openalex.org/W4415433365","https://openalex.org/W4415433705","https://openalex.org/W7133196460","https://openalex.org/W7140077390","https://openalex.org/W7155065514","https://openalex.org/W7155084225","https://openalex.org/W7164646448","https://openalex.org/W7164648746","https://openalex.org/W7164650202","https://openalex.org/W7164658445","https://openalex.org/W7164662832","https://openalex.org/W7164672802","https://openalex.org/W7164681742"],"related_works":["https://openalex.org/W7155084225","https://openalex.org/W2508092598","https://openalex.org/W7164681742","https://openalex.org/W4321600175","https://openalex.org/W3196777808","https://openalex.org/W2794289187","https://openalex.org/W4415433705","https://openalex.org/W7164662832","https://openalex.org/W7164658445","https://openalex.org/W2963978172"],"abstract_inverted_index":{"Humans":[0],"have":[1],"the":[2,76,80,114,140,155,161],"remarkable":[3],"ability":[4],"to":[5,14,33,85,120],"engage":[6],"in":[7,166],"spontaneous":[8],"informal":[9],"conversations":[10,56,124],"and":[11,51,112,125,143],"selectively":[12],"attend":[13],"individual":[15],"speakers":[16,50,122],"while":[17],"filtering":[18],"out":[19],"competing":[20],"speech":[21,34,101,106,146],"from":[22,57],"nearby":[23],"conversations.":[24],"This":[25],"\u201ccocktail":[26],"party\u201d":[27],"scenario":[28],"still":[29],"presents":[30],"severe":[31],"challenges":[32],"recognition":[35,107],"systems.":[36],"The":[37],"CHiME-9":[38],"MCoRec":[39],"task":[40],"provides":[41],"a":[42,65],"testbed":[43],"where":[44,79],"systems":[45],"must":[46],"recognize":[47],"groups":[48],"of":[49,54,68,116,139,164],"transcribe":[52],"each":[53,109],"their":[55],"audio-visual":[58,99,105],"input.":[59],"In":[60],"this":[61],"work,":[62],"we":[63],"analyze":[64],"diverse":[66],"set":[67],"systems,":[69],"representing":[70],"different":[71],"design":[72],"directions":[73,134],"for":[74,108],"addressing":[75],"cocktail-party":[77,141,167],"scenario,":[78],"best":[81],"system":[82],"achieves":[83],"up":[84],"57%":[86],"relative":[87],"error":[88],"reduction.":[89],"We":[90],"identify":[91],"three":[92],"main":[93],"strategies:":[94],"(1)":[95],"explicit":[96],"or":[97],"implicit":[98],"target":[100,110],"separation,":[102],"(2)":[103],"improved":[104],"speaker,":[111],"(3)":[113],"use":[115],"large":[117],"language":[118],"models":[119],"group":[121],"into":[123],"enhance":[126],"conversational":[127],"consistency.":[128],"Our":[129],"analysis":[130],"shows":[131],"that":[132,144,158],"these":[133],"address":[135],"complementary":[136],"failure":[137],"modes":[138],"problem,":[142],"high":[145],"overlap":[147,159],"alone":[148],"does":[149],"not":[150],"explain":[151],"performance":[152],"differences,":[153],"challenging":[154],"common":[156],"assumption":[157],"is":[160],"primary":[162],"source":[163],"difficulty":[165],"recognition.":[168]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-08-12T00:00:00"}
