{"id":"https://openalex.org/W4319862215","doi":"https://doi.org/10.1109/slt54892.2023.10023037","title":"End-to-End Multi-Speaker ASR with Independent Vector Analysis","display_name":"End-to-End Multi-Speaker ASR with Independent Vector Analysis","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862215","doi":"https://doi.org/10.1109/slt54892.2023.10023037"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023037","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/A5020401831","display_name":"Robin Scheibler","orcid":"https://orcid.org/0000-0002-5205-8365"},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Robin Scheibler","raw_affiliation_strings":["LINE Corporation,Tokyo,Japan","LINE Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,X-LANCE Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,China","Department of Computer Science and Engineering, X-LANCE Lab, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,X-LANCE Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, X-LANCE Lab, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University,Pittsburgh,USA","Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University,Pittsburgh,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University,Pittsburgh,USA","Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University,Pittsburgh,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,X-LANCE Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,China","Department of Computer Science and Engineering, X-LANCE Lab, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,X-LANCE Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, X-LANCE Lab, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"496","last_page":"501"},"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/T11447","display_name":"Blind Source Separation Techniques","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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8024255037307739},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6498203873634338},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5802751779556274},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5791979432106018},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5231515169143677},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5211532115936279},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4633529484272003},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4320105314254761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39213451743125916},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3905341923236847},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10777148604393005},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0965055525302887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8024255037307739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6498203873634338},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5802751779556274},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5791979432106018},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5231515169143677},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5211532115936279},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4633529484272003},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4320105314254761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39213451743125916},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3905341923236847},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10777148604393005},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0965055525302887},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023037","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":[{"id":"https://openalex.org/G5465080215","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G7198716103","display_name":null,"funder_award_id":"62122050,62071288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1506688500","https://openalex.org/W1543386260","https://openalex.org/W1552314771","https://openalex.org/W1845880232","https://openalex.org/W2072548008","https://openalex.org/W2089586791","https://openalex.org/W2114461480","https://openalex.org/W2127851351","https://openalex.org/W2164502538","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2517616541","https://openalex.org/W2526425061","https://openalex.org/W2602577565","https://openalex.org/W2640112133","https://openalex.org/W2734774145","https://openalex.org/W2763188033","https://openalex.org/W2767071179","https://openalex.org/W2806730552","https://openalex.org/W2886180730","https://openalex.org/W2905402910","https://openalex.org/W2933708090","https://openalex.org/W2954049404","https://openalex.org/W2962780374","https://openalex.org/W2963375116","https://openalex.org/W2972818416","https://openalex.org/W2987027330","https://openalex.org/W3007328579","https://openalex.org/W3008762051","https://openalex.org/W3015564447","https://openalex.org/W3015666015","https://openalex.org/W3015678657","https://openalex.org/W3015834770","https://openalex.org/W3016244615","https://openalex.org/W3028504434","https://openalex.org/W3086154751","https://openalex.org/W3096073522","https://openalex.org/W3099177480","https://openalex.org/W3130736950","https://openalex.org/W3162315798","https://openalex.org/W3163257865","https://openalex.org/W3168947150","https://openalex.org/W4205972622","https://openalex.org/W4212774754","https://openalex.org/W4256161595","https://openalex.org/W4295723153","https://openalex.org/W4296068789","https://openalex.org/W6752516136","https://openalex.org/W6766978945","https://openalex.org/W6775450108","https://openalex.org/W6790629284","https://openalex.org/W6799174933"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W2963170046","https://openalex.org/W2376244802","https://openalex.org/W4311414679","https://openalex.org/W2923631784","https://openalex.org/W818226659","https://openalex.org/W2158075901","https://openalex.org/W2151749779","https://openalex.org/W1999612375","https://openalex.org/W4319586017"],"abstract_inverted_index":{"We":[0,11,80],"develop":[1],"an":[2],"end-to-end":[3],"system":[4],"for":[5,15,109],"multi-channel,":[6],"multi-speaker":[7],"automatic":[8],"speech":[9],"recognition.":[10],"propose":[12],"a":[13,41,145],"frontend":[14,120],"joint":[16],"source":[17,36,43,70],"separation":[18],"and":[19,33,67,111,141],"dereverberation":[20],"based":[21],"on":[22,123,129,148],"the":[23,31,49,64,68,76,95,101,117],"independent":[24],"vector":[25],"analysis":[26],"(IVA)":[27],"paradigm.":[28],"It":[29],"uses":[30],"fast":[32],"stable":[34],"iterative":[35],"steering":[37],"algorithm":[38],"together":[39],"with":[40,84,91,144],"neural":[42,47,69,88],"model.":[44],"Unlike":[45],"conventional":[46],"beamforming,":[48],"number":[50,106],"of":[51,94,107,137,139,150],"speakers":[52,143],"can":[53],"be":[54],"dynamically":[55],"changed":[56],"during":[57],"or":[58],"after":[59],"training.":[60],"The":[61],"parameters":[62],"from":[63,75],"ASR":[65,77],"module":[66],"model":[71,146],"are":[72],"optimized":[73],"jointly":[74],"loss":[78],"itself.":[79],"demonstrate":[81,115,135],"competitive":[82],"performance":[83],"previous":[85],"systems":[86],"using":[87,104],"beamforming":[89],"frontends":[90],"only":[92],"one-ninth":[93],"trainable":[96],"parameter.":[97],"First,":[98],"we":[99,114,134],"explore":[100],"trade-offs":[102],"when":[103,127],"various":[105],"channels":[108],"training":[110],"testing.":[112],"Second,":[113],"that":[116],"proposed":[118],"IVA":[119],"performs":[121],"well":[122],"noisy":[124],"data,":[125],"even":[126],"trained":[128,147],"clean":[130],"mixtures":[131,138,149],"only.":[132,152],"Third,":[133],"recognition":[136],"three":[140],"four":[142],"two":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}