{"id":"https://openalex.org/W4221165517","doi":"https://doi.org/10.1109/icassp43922.2022.9747067","title":"The USTC-Ximalaya System for the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription (M2met) Challenge","display_name":"The USTC-Ximalaya System for the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription (M2met) Challenge","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221165517","doi":"https://doi.org/10.1109/icassp43922.2022.9747067"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747067","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5018657729","display_name":"Maokui He","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":true,"raw_author_name":"Maokui He","raw_affiliation_strings":["University of Science and Technology of China,HeFei,China","University of Science and Technology of China, HeFei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,HeFei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, HeFei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100984497","display_name":"Xiang Lv","orcid":"https://orcid.org/0000-0002-0032-5492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Lv","raw_affiliation_strings":["Ximalaya Inc.,ShangHai,China","Ximalaya Inc., ShangHai, China"],"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,ShangHai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., ShangHai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113903050","display_name":"Weilin Zhou","orcid":"https://orcid.org/0009-0009-2615-6306"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weilin Zhou","raw_affiliation_strings":["Ximalaya Inc.,ShangHai,China","Ximalaya Inc., ShangHai, China"],"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,ShangHai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., ShangHai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004857861","display_name":"Jingjing Yin","orcid":"https://orcid.org/0000-0003-4843-613X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"JingJing Yin","raw_affiliation_strings":["Ximalaya Inc.,ShangHai,China","Ximalaya Inc., ShangHai, China"],"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,ShangHai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., ShangHai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120274206","display_name":"Xiaoqi Zhang","orcid":"https://orcid.org/0000-0003-0707-0928"},"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":"Xiaoqi Zhang","raw_affiliation_strings":["University of Science and Technology of China,HeFei,China","University of Science and Technology of China, HeFei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,HeFei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, HeFei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103854502","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-8269-3354"},"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":"Yuxuan Wang","raw_affiliation_strings":["University of Science and Technology of China,HeFei,China","University of Science and Technology of China, HeFei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,HeFei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, HeFei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064699619","display_name":"Shutong Niu","orcid":"https://orcid.org/0000-0003-0315-1042"},"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":"Shutong Niu","raw_affiliation_strings":["University of Science and Technology of China,HeFei,China","University of Science and Technology of China, HeFei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,HeFei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, HeFei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010183483","display_name":"Yuhang Cao","orcid":"https://orcid.org/0009-0008-3627-590X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhang Cao","raw_affiliation_strings":["Ximalaya Inc.,ShangHai,China","Ximalaya Inc., ShangHai, China"],"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,ShangHai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., ShangHai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Lu","raw_affiliation_strings":["Ximalaya Inc.,ShangHai,China","Ximalaya Inc., ShangHai, China"],"affiliations":[{"raw_affiliation_string":"Ximalaya Inc.,ShangHai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc., ShangHai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"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":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,HeFei,China","University of Science and Technology of China, HeFei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,HeFei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, HeFei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5018657729"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.6579401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"9166","last_page":"9170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.9972000122070312,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8264073133468628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7230733036994934},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7118455767631531},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.667156994342804},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6219778060913086},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5869362950325012},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5266287922859192},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45256099104881287},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41243818402290344},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3577038049697876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33265161514282227},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.19995135068893433}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8264073133468628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7230733036994934},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7118455767631531},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.667156994342804},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6219778060913086},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5869362950325012},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5266287922859192},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45256099104881287},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41243818402290344},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3577038049697876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33265161514282227},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.19995135068893433},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747067","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1606894530","https://openalex.org/W1965819578","https://openalex.org/W1983812858","https://openalex.org/W2117678320","https://openalex.org/W2219249508","https://openalex.org/W2748661748","https://openalex.org/W2765407302","https://openalex.org/W2889048668","https://openalex.org/W2915347754","https://openalex.org/W2963197115","https://openalex.org/W2972492143","https://openalex.org/W2972949456","https://openalex.org/W2997419692","https://openalex.org/W3008357631","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3095212884","https://openalex.org/W3105031100","https://openalex.org/W3178462146","https://openalex.org/W3195050710","https://openalex.org/W3198133542","https://openalex.org/W3207834622","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6745136726","https://openalex.org/W6754473786","https://openalex.org/W6766380642"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"We":[0],"propose":[1],"two":[2],"improvements":[3],"to":[4,22,35,92,98,130],"target-speaker":[5],"voice":[6],"activity":[7],"detection":[8],"(TS-VAD),":[9],"the":[10,23,94,106,109,126,141],"core":[11],"component":[12],"in":[13,39,60,77,116],"our":[14,121],"proposed":[15,122],"speaker":[16],"diarization":[17,100,139],"system":[18,123],"that":[19,120],"was":[20],"submitted":[21],"2022":[24],"Multi-Channel":[25],"Multi-Party":[26],"Meeting":[27],"Transcription":[28],"(M2MeT)":[29],"challenge.":[30],"These":[31],"techniques":[32],"are":[33,74],"designed":[34],"handle":[36],"multi-speaker":[37],"conversations":[38,73],"real-world":[40],"meeting":[41,113],"scenarios":[42],"with":[43,135],"high":[44],"speaker-overlap":[45],"ratios":[46],"and":[47,51,58,70],"under":[48],"heavy":[49],"reverberant":[50],"noisy":[52],"condition.":[53],"First,":[54],"for":[55],"data":[56,65],"preparation":[57],"augmentation":[59],"training":[61],"TS-VAD":[62,82],"models,":[63],"speech":[64],"containing":[66],"both":[67],"real":[68],"meetings":[69],"simulated":[71],"indoor":[72],"used.":[75],"Second,":[76],"refining":[78],"results":[79,96],"obtained":[80],"after":[81],"based":[83,138],"decoding,":[84],"we":[85,118],"perform":[86],"a":[87],"series":[88],"of":[89],"post-processing":[90],"steps":[91],"improve":[93],"VAD":[95],"needed":[97],"reduce":[99],"error":[101],"rates":[102],"(DERs).":[103],"Tested":[104],"on":[105,140],"ALIMEETING":[107],"corpus,":[108],"newly":[110],"released":[111],"Mandarin":[112],"dataset":[114],"used":[115],"M2MeT,":[117],"demonstrate":[119],"can":[124],"decrease":[125],"DER":[127],"by":[128],"up":[129],"66.55/60.59%":[131],"relatively":[132],"when":[133],"compared":[134],"classical":[136],"clustering":[137],"Eval/Test":[142],"set.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
