{"id":"https://openalex.org/W4388821012","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317185","title":"A Comparative Study on Multichannel Speaker-Attributed Automatic Speech Recognition in Multi-party Meetings","display_name":"A Comparative Study on Multichannel Speaker-Attributed Automatic Speech Recognition in Multi-party Meetings","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388821012","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317185"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317185","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/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 (USTC),NERC-SLIP,China","NERC-SLIP, University of Science and Technology of China (USTC), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436848","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-1124-0854"},"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":"Jie Zhang","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,China","NERC-SLIP, University of Science and Technology of China (USTC), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), 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/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Du","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346632","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0003-3147-7269"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428456","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0002-1909-302X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"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/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"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":"Li-Rong Dai","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,China","NERC-SLIP, University of Science and Technology of China (USTC), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"1943","last_page":"1948"},"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.792914867401123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7856734991073608},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7424042224884033},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6825336217880249},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6000489592552185},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5465580224990845},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.466980904340744},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.46215111017227173},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45243149995803833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4110037684440613},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0969109833240509},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07546466588973999}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.792914867401123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7856734991073608},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7424042224884033},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6825336217880249},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6000489592552185},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5465580224990845},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.466980904340744},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.46215111017227173},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45243149995803833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4110037684440613},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0969109833240509},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07546466588973999},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317185","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1876378865","https://openalex.org/W2061074721","https://openalex.org/W2208299922","https://openalex.org/W2550143307","https://openalex.org/W2726515241","https://openalex.org/W2738829388","https://openalex.org/W2760103357","https://openalex.org/W2808631503","https://openalex.org/W2884797218","https://openalex.org/W2915347754","https://openalex.org/W2962780374","https://openalex.org/W2963773971","https://openalex.org/W2964058413","https://openalex.org/W3004309045","https://openalex.org/W3008762051","https://openalex.org/W3015372568","https://openalex.org/W3025260599","https://openalex.org/W3094821064","https://openalex.org/W3094893851","https://openalex.org/W3095300891","https://openalex.org/W3097777922","https://openalex.org/W3099832538","https://openalex.org/W3160207687","https://openalex.org/W3169722760","https://openalex.org/W3195050710","https://openalex.org/W3196595845","https://openalex.org/W3196940724","https://openalex.org/W3198511309","https://openalex.org/W3207834622","https://openalex.org/W4221165341","https://openalex.org/W4224916733","https://openalex.org/W4224925136","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6688039610"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"Speaker-attributed":[0],"automatic":[1],"speech":[2],"recognition":[3],"(SA-ASR)":[4],"in":[5,124],"multi-party":[6],"meeting":[7],"scenarios":[8],"is":[9],"one":[10],"of":[11,40,126],"the":[12,56,59,107,120,127],"most":[13],"valuable":[14],"and":[15,37,44,76,99],"challenging":[16],"ASR":[17,45],"tasks.":[18],"It":[19],"was":[20],"shown":[21],"that":[22,111],"SingleChannel":[23],"Frame-level":[24],"Diarization":[25,33],"with":[26,34],"Serialized":[27],"Output":[28],"Training":[29],"(SC-FD-SOT),":[30],"Single-Channel":[31,41],"Word-level":[32],"SOT":[35],"(SC-WD-SOT),":[36],"joint":[38],"training":[39],"Target-Speaker":[42],"separation":[43],"(SC-TS-ASR)":[46],"can":[47,117],"be":[48],"exploited":[49],"to":[50],"partially":[51],"solve":[52],"this":[53,63],"problem,":[54],"where":[55],"latter":[57],"achieves":[58],"best":[60],"performance.":[61],"In":[62],"paper,":[64],"we":[65],"propose":[66],"three":[67],"corresponding":[68,121],"MultiChannel":[69],"(MC)":[70],"SA-ASR":[71,115],"approaches,":[72],"namely":[73],"MC-FD-SOT,":[74,93],"MC-WD-SOT,":[75],"MC-TS-ASR.":[77,103],"For":[78],"different":[79,81],"tasks/models,":[80],"multichannel":[82,114],"data":[83],"fusion":[84],"strategies":[85],"are":[86],"considered,":[87],"including":[88],"channel-level":[89],"cross-channel":[90,95],"attention":[91,96],"for":[92,97,102],"frame-level":[94],"MC-WD-SOT":[98],"neural":[100],"beamforming":[101],"Experimental":[104],"results":[105],"on":[106],"Al-iMeeting":[108],"corpus":[109],"reveal":[110],"our":[112],"proposed":[113],"models":[116],"consistently":[118],"outperform":[119],"single-channel":[122],"counterparts":[123],"terms":[125],"speaker-dependent":[128],"character":[129],"error":[130],"rate":[131],"(SD-CER).":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}