{"id":"https://openalex.org/W7148249352","doi":"https://doi.org/10.1109/asru65441.2025.11434706","title":"Non-Autoregressive Multi-Speaker ASR with Decoupled Speaker Change Detection","display_name":"Non-Autoregressive Multi-Speaker ASR with Decoupled Speaker Change Detection","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148249352","doi":"https://doi.org/10.1109/asru65441.2025.11434706"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132739347","display_name":"Yingke Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090344","display_name":"Fano Labs (China)","ror":"https://ror.org/008jsgk36","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210090344"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yingke Zhu","raw_affiliation_strings":["Fano,Hong Kong,SAR,China"],"affiliations":[{"raw_affiliation_string":"Fano,Hong Kong,SAR,China","institution_ids":["https://openalex.org/I4210090344"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004424826","display_name":"Lahiru Samarakoon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090344","display_name":"Fano Labs (China)","ror":"https://ror.org/008jsgk36","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210090344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lahiru Samarakoon","raw_affiliation_strings":["Fano,Hong Kong,SAR,China"],"affiliations":[{"raw_affiliation_string":"Fano,Hong Kong,SAR,China","institution_ids":["https://openalex.org/I4210090344"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5132739347"],"corresponding_institution_ids":["https://openalex.org/I4210090344"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87546307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7904999852180481,"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":0.7904999852180481,"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":0.05999999865889549,"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/T10057","display_name":"Face and Expression Recognition","score":0.04010000079870224,"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/noise","display_name":"Noise (video)","score":0.36000001430511475},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3504999876022339},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.3278999924659729},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.28369998931884766},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.2782000005245209}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5637000203132629},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5200999975204468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3693000078201294},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2418999969959259}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5124868750572205,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2747874407","https://openalex.org/W2766219058","https://openalex.org/W2889503488","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2963843276","https://openalex.org/W3008762051","https://openalex.org/W3013139777","https://openalex.org/W3015746570","https://openalex.org/W3015834770","https://openalex.org/W3020336359","https://openalex.org/W3097643313","https://openalex.org/W3097777922","https://openalex.org/W3109079702","https://openalex.org/W3162847598","https://openalex.org/W3181056718","https://openalex.org/W3196194966","https://openalex.org/W3198522318","https://openalex.org/W4226491018","https://openalex.org/W4283067311","https://openalex.org/W4297727296","https://openalex.org/W4319862215","https://openalex.org/W4372342485","https://openalex.org/W4375869109","https://openalex.org/W4385822334","https://openalex.org/W4387010481","https://openalex.org/W4391021006","https://openalex.org/W4392904528"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"multi-speaker":[1,29],"automatic":[2],"speech":[3,41],"recognition":[4,42],"(ASR)":[5],"approaches":[6],"predominantly":[7],"rely":[8],"on":[9,106,110],"autoregressive":[10],"(AR)":[11],"decoding.":[12],"The":[13],"AR":[14,142],"decoding":[15,67,73,128],"complicates":[16],"the":[17,75,81,93,97],"parallel":[18],"computation.":[19],"In":[20],"this":[21],"work":[22],"we":[23],"explore":[24],"non-autoregressive":[25],"(NAR)":[26],"models":[27],"for":[28],"ASR":[30,36,66,76],"to":[31,139],"achieve":[32],"faster":[33],"inference.":[34],"Multi-speaker":[35],"comprises":[37],"two":[38,64],"primary":[39],"tasks:":[40],"and":[43,78,108],"speaker":[44,82],"change":[45],"detection":[46],"(SCD).":[47],"We":[48],"introduce":[49],"a":[50,100,116,124,132,140],"framework":[51],"that":[52,89],"decouples":[53],"these":[54],"tasks":[55],"into":[56],"separate":[57],"branches.":[58],"Inference":[59],"is":[60,68],"carried":[61],"out":[62],"in":[63,84,113,127,136],"stages:":[65],"performed":[69],"first,":[70],"then":[71],"SCD":[72],"leverages":[74],"output":[77],"predicts":[79],"all":[80],"changes":[83],"one":[85],"pass.":[86],"Experiments":[87],"show":[88],"with":[90,115,130],"NAR":[91,121],"decoding,":[92],"proposed":[94],"model":[95,122],"outperforms":[96],"baseline":[98],"by":[99],"relative":[101],"cpWER":[102],"reduction":[103,135],"of":[104],"30%":[105],"LibriSpeechMix":[107],"8%":[109],"AMI.":[111],"Additionally,":[112],"scenarios":[114],"10%":[117],"overlap":[118],"ratio,":[119],"our":[120],"achieves":[123],"threefold":[125],"increase":[126],"speed":[129],"only":[131],"1.2":[133],"%":[134],"accuracy":[137],"compared":[138],"strong":[141],"baseline.":[143]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}