{"id":"https://openalex.org/W4319862656","doi":"https://doi.org/10.1109/slt54892.2023.10022715","title":"MFCCA:Multi-Frame Cross-Channel Attention for Multi-Speaker ASR in Multi-Party Meeting Scenario","display_name":"MFCCA:Multi-Frame Cross-Channel Attention for Multi-Speaker ASR in Multi-Party Meeting Scenario","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862656","doi":"https://doi.org/10.1109/slt54892.2023.10022715"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022715","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5100616400","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0002-0576-7396"},"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":"Fan Yu","raw_affiliation_strings":["School of Computer Science, Northwestern Poly technical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Poly technical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055433405","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0001-9053-9314"},"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":"Shiliang Zhang","raw_affiliation_strings":["School of Computer Science, Northwestern Poly technical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Poly technical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China","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":["School of Computer Science, Northwestern Poly technical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Poly technical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"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":["School of Computer Science, Northwestern Poly technical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Poly technical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"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/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":"Zhihao Du","raw_affiliation_strings":["School of Computer Science, Northwestern Poly technical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Poly technical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022192867","display_name":"Yuxiao Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiao Lin","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University,Hangzhou,China","College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"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":["School of Computer Science, Northwestern Poly technical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Poly technical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"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":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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/T11309","display_name":"Music 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7923766374588013},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.7308288216590881},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5561187267303467},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5291334390640259},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.515772819519043},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4744338095188141},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4700421690940857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3931460976600647},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.22860252857208252},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07165271043777466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7923766374588013},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.7308288216590881},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5561187267303467},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5291334390640259},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.515772819519043},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4744338095188141},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4700421690940857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3931460976600647},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.22860252857208252},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07165271043777466},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022715","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":43,"referenced_works":["https://openalex.org/W1499712254","https://openalex.org/W1876378865","https://openalex.org/W2398042854","https://openalex.org/W2460742184","https://openalex.org/W2517616541","https://openalex.org/W2738829388","https://openalex.org/W2747732471","https://openalex.org/W2884797218","https://openalex.org/W2899625056","https://openalex.org/W2900440209","https://openalex.org/W2915347754","https://openalex.org/W2939690918","https://openalex.org/W2962780374","https://openalex.org/W2962866211","https://openalex.org/W2963773971","https://openalex.org/W2998616931","https://openalex.org/W3013139777","https://openalex.org/W3015791598","https://openalex.org/W3015834770","https://openalex.org/W3016131876","https://openalex.org/W3020336359","https://openalex.org/W3094893851","https://openalex.org/W3095300891","https://openalex.org/W3096073522","https://openalex.org/W3096408984","https://openalex.org/W3097777922","https://openalex.org/W3099832538","https://openalex.org/W3133848124","https://openalex.org/W3160207687","https://openalex.org/W3161587262","https://openalex.org/W3169722760","https://openalex.org/W3196117288","https://openalex.org/W3207570488","https://openalex.org/W3207834622","https://openalex.org/W4221165341","https://openalex.org/W4221165543","https://openalex.org/W4224916733","https://openalex.org/W4224933780","https://openalex.org/W4385245566","https://openalex.org/W6633847657","https://openalex.org/W6773628751","https://openalex.org/W6784531339","https://openalex.org/W6810532824"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Recently":[0],"cross-channel":[1,55,59],"attention,":[2,56],"which":[3,57],"better":[4],"leverages":[5],"multi-channel":[6,165],"signals":[7],"from":[8],"microphone":[9,47],"array,":[10],"has":[11],"shown":[12],"promising":[13],"results":[14],"in":[15,157],"the":[16,44,66,84,95,106,147,153,158],"multi-party":[17],"meeting":[18],"scenario.":[19],"Cross-channel":[20],"attention":[21],"focuses":[22],"on":[23,105,125,146],"either":[24],"learning":[25],"global":[26],"correlations":[27],"between":[28,61,100],"sequences":[29],"of":[30,46,68],"different":[31],"channels":[32],"or":[33],"exploiting":[34],"fine-grained":[35],"channel-wise":[36,72],"information":[37,60],"effectively":[38],"at":[39],"each":[40],"time":[41],"step.":[42],"Considering":[43],"delay":[45],"array":[48],"receiving":[49],"sound,":[50],"we":[51,75],"propose":[52,77],"a":[53,78,89,108,142,162],"multi-frame":[54],"models":[58],"adjacent":[62],"frames":[63],"to":[64,82,93],"exploit":[65],"complementarity":[67],"both":[69],"frame-wise":[70],"and":[71,88,102,121,127,135],"knowledge.":[73],"Besides,":[74],"also":[76],"multi-layer":[79],"convolutional":[80],"mechanism":[81],"fuse":[83],"multi":[85],"-channel":[86],"output":[87],"channel":[90,96],"masking":[91],"strategy":[92],"combat":[94],"number":[97],"mismatch":[98],"problem":[99],"training":[101,136],"inference.":[103],"Experiments":[104],"AliMeeting,":[107],"real-world":[109],"corpus,":[110,149],"reveal":[111],"that":[112],"our":[113,138],"proposed":[114,139],"model":[115,118,133,140],"outperforms":[116],"single-channel":[117],"by":[119],"31.7%":[120],"37.0%":[122],"CER":[123],"reduction":[124],"Eval":[126],"Test":[128],"sets.":[129],"Moreover,":[130],"with":[131,152],"comparable":[132],"parameters":[134],"data,":[137],"achieves":[141],"new":[143],"SOTA":[144],"performance":[145],"AliMeeting":[148],"as":[150],"compared":[151],"top":[154],"ranking":[155],"systems":[156],"ICASSP2022":[159],"M2MeT":[160],"challenge,":[161],"recently":[163],"held":[164],"multi-speaker":[166],"ASR":[167],"challenge.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}