{"id":"https://openalex.org/W4391021006","doi":"https://doi.org/10.1109/asru57964.2023.10389762","title":"Sa-Paraformer: Non-Autoregressive End-To-End Speaker-Attributed ASR","display_name":"Sa-Paraformer: Non-Autoregressive End-To-End Speaker-Attributed ASR","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021006","doi":"https://doi.org/10.1109/asru57964.2023.10389762"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5104231255","display_name":"Yangze Li","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangze Li","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU)","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616400","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0002-0576-7396"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":["Speech Lab of DAMO Academy,Alibaba Group","Alibaba Group, Speech Lab of DAMO Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab of DAMO Academy,Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Alibaba Group, Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102543677","display_name":"Yuhao Liang","orcid":"https://orcid.org/0009-0008-9516-6594"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Liang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU)","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU)","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069196598","display_name":"Mohan Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mohan Shi","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001133136","display_name":"Zhihao Du","orcid":"https://orcid.org/0000-0003-3509-9322"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Zhihao Du","raw_affiliation_strings":["Speech Lab of DAMO Academy,Alibaba Group","Alibaba Group, Speech Lab of DAMO Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab of DAMO Academy,Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Alibaba Group, Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777591","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0002-9524-1602"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Speech Lab of DAMO Academy,Alibaba Group","Alibaba Group, Speech Lab of DAMO Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab of DAMO Academy,Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Alibaba Group, Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU)","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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/autoregressive-model","display_name":"Autoregressive model","score":0.7094007134437561},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6956571340560913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6512337923049927},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5832631587982178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.169429212808609},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11709558963775635},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.08330720663070679}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7094007134437561},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6956571340560913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6512337923049927},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5832631587982178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.169429212808609},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11709558963775635},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.08330720663070679}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1876378865","https://openalex.org/W2046056978","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2726515241","https://openalex.org/W2738829388","https://openalex.org/W2884797218","https://openalex.org/W2915347754","https://openalex.org/W2963773971","https://openalex.org/W3008357631","https://openalex.org/W3008762051","https://openalex.org/W3013139777","https://openalex.org/W3016167541","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3095212884","https://openalex.org/W3096571892","https://openalex.org/W3097643313","https://openalex.org/W3097777922","https://openalex.org/W3097882114","https://openalex.org/W3099832538","https://openalex.org/W3143843080","https://openalex.org/W3162249256","https://openalex.org/W3162315798","https://openalex.org/W3196194966","https://openalex.org/W3196595845","https://openalex.org/W3198522318","https://openalex.org/W3207834622","https://openalex.org/W3211278025","https://openalex.org/W3212886388","https://openalex.org/W4224925136","https://openalex.org/W4226305408","https://openalex.org/W4226418945","https://openalex.org/W4226491018","https://openalex.org/W4283067311","https://openalex.org/W4319862656","https://openalex.org/W4385823501","https://openalex.org/W6633847657","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W4327525404"],"abstract_inverted_index":{"Joint":[0],"modeling":[1],"of":[2,28,147],"multi-speaker":[3],"ASR":[4],"and":[5,42,99],"speaker":[6,96],"diarization":[7],"has":[8],"recently":[9,57],"shown":[10],"promising":[11],"results":[12,43],"in":[13,44,66,109],"speaker-attributed":[14],"automatic":[15],"speech":[16],"recognition":[17],"(SA-ASR).":[18],"Although":[19],"being":[20],"able":[21],"to":[22,75,82,94,104],"obtain":[23],"state-of-the-art":[24],"(SOTA)":[25],"performance,":[26],"most":[27],"the":[29,67,83,106,114,122,137,155],"studies":[30],"are":[31],"based":[32],"on":[33,113,136],"an":[34,63,101],"autoregressive":[35],"(AR)":[36],"decoder":[37,74],"which":[38],"generates":[39],"tokens":[40],"one-by-one":[41],"a":[45,56,72,91,127,144],"large":[46],"real-time":[47],"factor":[48],"(RTF).":[49],"To":[50],"speed":[51],"up":[52],"inference,":[53],"we":[54,89],"introduce":[55],"proposed":[58],"non-autoregressive":[59],"model":[60,65,120,125,142],"Paraformer":[61,70],"as":[62],"acoustic":[64,110],"SA-ASR":[68,124,159],"model.":[69,160],"uses":[71],"single-step":[73],"enable":[76],"parallel":[77],"generation,":[78],"obtaining":[79],"comparable":[80,145],"performance":[81],"SOTA":[84,156],"AR":[85,158],"transformer":[86],"models.":[87],"Besides,":[88],"propose":[90],"speaker-filling":[92],"strategy":[93,103],"reduce":[95],"identification":[97],"errors":[98],"adopt":[100],"inter-CTC":[102],"enhance":[105],"encoder\u2019s":[107],"ability":[108],"modeling.":[111],"Experiments":[112],"AliMeeting":[115],"corpus":[116],"show":[117],"that":[118],"our":[119,141],"outperforms":[121],"cascaded":[123],"by":[126],"6.1%":[128],"relative":[129],"speaker-dependent":[130],"character":[131],"error":[132],"rate":[133],"(SD-CER)":[134],"reduction":[135],"test":[138],"set.":[139],"Moreover,":[140],"achieves":[143],"SD-CER":[146],"34.8%":[148],"with":[149,154],"only":[150],"1/10":[151],"RTF":[152],"compared":[153],"joint":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}