{"id":"https://openalex.org/W7225744041","doi":"https://doi.org/10.48550/arxiv.2611.10659","title":"Pandemonium: Longform Target-Speaker Speech Recognition with Cross-Speaker Interactions","display_name":"Pandemonium: Longform Target-Speaker Speech Recognition with Cross-Speaker Interactions","publication_year":2026,"publication_date":"2026-11-07","ids":{"openalex":"https://openalex.org/W7225744041","doi":"https://doi.org/10.48550/arxiv.2611.10659"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.10659","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.10659","pdf_url":"https://arxiv.org/pdf/2611.10659","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.10659","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114369422","display_name":"Alexander Polok","orcid":"https://orcid.org/0009-0000-4958-202X","observed_orcids":["https://orcid.org/0009-0000-4958-202X"]},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Polok, Alexander","raw_affiliation_strings":["Brno University of Technology , Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology , Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090369622","display_name":"Dominik Klement","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Klement, Dominik","raw_affiliation_strings":["Brno University of Technology , Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology , Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022587932","display_name":"Ivan Medennikov","orcid":"https://orcid.org/0000-0001-5381-3433","observed_orcids":["https://orcid.org/0000-0001-5381-3433"]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Medennikov, Ivan","raw_affiliation_strings":["NVIDIA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025212823","display_name":"Antoine Laurent","orcid":"https://orcid.org/0000-0002-2653-1008","observed_orcids":["https://orcid.org/0000-0002-2653-1008","https://orcid.org/0000-0002-3727-5644"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laurent, Antoine","raw_affiliation_strings":["pyannoteAI , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"pyannoteAI , France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130014188","display_name":"Petr P\u00e1lka","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"P\u00e1lka, Petr","raw_affiliation_strings":["Brno University of Technology , Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology , Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047682990","display_name":"Samuele Cornell","orcid":"https://orcid.org/0000-0002-5358-1844","observed_orcids":["https://orcid.org/0000-0002-5358-1844"]},"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":"Cornell, Samuele","raw_affiliation_strings":["Carnegie Mellon University , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University , USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161413155","display_name":"Shinji Watanabe","orcid":null,"observed_orcids":[]},"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":"Watanabe, Shinji","raw_affiliation_strings":["Carnegie Mellon University , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University , USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev P. Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897","observed_orcids":["https://orcid.org/0000-0001-5976-0897"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khudanpur, Sanjeev","raw_affiliation_strings":["Johns Hopkins University , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University , USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040747392","display_name":"Jagadeesh Balam","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Balam, Jagadeesh","raw_affiliation_strings":["NVIDIA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210","observed_orcids":["https://orcid.org/0000-0002-8800-0210"]},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"\u010cernock\u00fd, Jan","raw_affiliation_strings":["Brno University of Technology , Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology , Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908","observed_orcids":["https://orcid.org/0000-0002-4951-5908"]},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Burget, Luk\u00e1\u0161","raw_affiliation_strings":["Brno University of Technology , Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology , Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014455067","display_name":"Matthew Wiesner","orcid":"https://orcid.org/0000-0001-8653-7738","observed_orcids":["https://orcid.org/0000-0001-8653-7738"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wiesner, Matthew","raw_affiliation_strings":["Johns Hopkins University , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University , USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.0006000000284984708,"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/T12031","display_name":"Speech and dialogue systems","score":9.999999747378752e-05,"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/parakeets","display_name":"parakeets","score":0.7149999737739563},{"id":"https://openalex.org/keywords/pseudo-labeling","display_name":"pseudo-labeling","score":0.968999981880188},{"id":"https://openalex.org/keywords/meeting-transcription","display_name":"meeting transcription","score":0.5040000081062317}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7501000165939331},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7170000076293945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6978999972343445},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5681999921798706},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3953999876976013},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3411000072956085},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.10659","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.10659","pdf_url":"https://arxiv.org/pdf/2611.10659","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2611.10659","doi":"https://doi.org/10.48550/arxiv.2611.10659","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.10659","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.10659","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.10659","pdf_url":"https://arxiv.org/pdf/2611.10659","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225744041.pdf","grobid_xml":"https://content.openalex.org/works/W7225744041.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W3027008958","https://openalex.org/W4416255707","https://openalex.org/W7125811016","https://openalex.org/W7126278909","https://openalex.org/W7140314540","https://openalex.org/W7161546649","https://openalex.org/W7171552453","https://openalex.org/W7212181524"],"related_works":["https://openalex.org/W4407156046","https://openalex.org/W3025834604","https://openalex.org/W4414969717","https://openalex.org/W7155974694","https://openalex.org/W7155105643","https://openalex.org/W7204210763","https://openalex.org/W4417097405","https://openalex.org/W7138833740","https://openalex.org/W7165050890","https://openalex.org/W7130421337"],"abstract_inverted_index":{"Diarization-conditioned":[0,6],"target-speaker":[1],"ASR":[2],"(TS-ASR),":[3],"in":[4,80],"particular":[5],"Whisper":[7],"(DiCoW),":[8],"is":[9,99],"an":[10,83],"accurate":[11],"and":[12,36,40,60,82,122,138,140],"data-efficient":[13],"approach":[14],"to":[15],"multi-talker":[16],"transcription.":[17],"It":[18],"has,":[19],"however,":[20],"three":[21],"structural":[22],"limitations:":[23],"the":[24,46,51,66,70,89,134,141],"model":[25,67],"transcribes":[26],"each":[27],"speaker":[28,71],"independently,":[29],"operates":[30],"on":[31],"short":[32],"(30":[33],"s)":[34],"windows,":[35],"optimizes":[37],"its":[38],"diarization":[39,52],"TS-ASR":[41],"components":[42],"separately.":[43],"We":[44,49,132],"address":[45],"first":[47],"two.":[48],"integrate":[50],"conditioning":[53],"into":[54],"a":[55,105],"longform":[56],"Parakeet":[57],"backbone":[58],"(DiCoP)":[59],"add":[61],"cross-speaker":[62],"attention,":[63],"which":[64],"lets":[65],"attend":[68],"across":[69,128],"dimension":[72],"so":[73],"that":[74,87,108],"speakers":[75],"are":[76],"no":[77],"longer":[78],"decoded":[79],"isolation,":[81],"STNO":[84],"mask":[85],"refiner":[86],"re-estimates":[88],"diarization-derived":[90],"conditioning.":[91],"As":[92],"conversational":[93],"data":[94,124],"with":[95,104,120],"genuine":[96],"multi-speaker":[97,114],"interaction":[98],"scarce,":[100],"we":[101],"scale":[102],"training":[103],"pseudo-labeling":[106],"pipeline":[107],"mines":[109],"5.4k":[110],"hours":[111],"of":[112],"in-the-wild":[113],"audio":[115],"from":[116],"YODAS2.":[117],"Combining":[118],"these":[119],"synthetic":[121],"real":[123],"yields":[125],"state-of-the-art":[126],"results":[127],"several":[129],"meeting":[130],"benchmarks.":[131],"open-source":[133],"resulting":[135],"models,":[136],"DiCoP":[137],"Pandemonium,":[139],"pseudo-labeled":[142],"data.":[143]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-11T00:00:00"}