{"id":"https://openalex.org/W3094831814","doi":"https://doi.org/10.1109/slt48900.2021.9383556","title":"Integration of Speech Separation, Diarization, and Recognition for Multi-Speaker Meetings: System Description, Comparison, and Analysis","display_name":"Integration of Speech Separation, Diarization, and Recognition for Multi-Speaker Meetings: System Description, Comparison, and Analysis","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3094831814","doi":"https://doi.org/10.1109/slt48900.2021.9383556","mag":"3094831814"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5004777817","display_name":"Desh Raj","orcid":"https://orcid.org/0000-0002-5038-9400"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Desh Raj","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081451455","display_name":"Pavel Denisov","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pavel Denisov","raw_affiliation_strings":["Institute for Natural Language Processing, University of Stuttgart, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing, University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft Corp, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Google Research, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101619225","display_name":"Zili Huang","orcid":"https://orcid.org/0000-0003-1238-8017"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zili Huang","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Maokui He","raw_affiliation_strings":["Columbia University, NY","University of Science and Technology of China, HeFei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, NY","institution_ids":["https://openalex.org/I78577930"]},{"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/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD","institution_ids":["https://openalex.org/I145311948"]}]},{"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"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["Columbia University, NY","University of Science and Technology of China, HeFei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, NY","institution_ids":["https://openalex.org/I78577930"]},{"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/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft Corp, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Luo","raw_affiliation_strings":["Columbia University, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, NY","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Microsoft Corp, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corp, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053447215","display_name":"Scott Wisdom","orcid":"https://orcid.org/0000-0001-6671-1428"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Wisdom","raw_affiliation_strings":["Google Research, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Google Research, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"897","last_page":"904"},"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.9335683584213257},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7992715835571289},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7723913788795471},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7155358195304871},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6303256750106812},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5533841252326965},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4976547062397003},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4199315905570984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40485575795173645},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08935567736625671}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9335683584213257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992715835571289},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7723913788795471},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7155358195304871},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6303256750106812},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5533841252326965},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4976547062397003},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4199315905570984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40485575795173645},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08935567736625671},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1558276682","https://openalex.org/W2125336414","https://openalex.org/W2127851351","https://openalex.org/W2514741789","https://openalex.org/W2526425061","https://openalex.org/W2533523411","https://openalex.org/W2638067502","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2734774145","https://openalex.org/W2802201485","https://openalex.org/W2803322398","https://openalex.org/W2888867175","https://openalex.org/W2890964092","https://openalex.org/W2891833136","https://openalex.org/W2900212944","https://openalex.org/W2936774411","https://openalex.org/W2937170468","https://openalex.org/W2939246703","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2960140743","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2964391865","https://openalex.org/W2972449503","https://openalex.org/W2972680151","https://openalex.org/W2972818416","https://openalex.org/W2995181338","https://openalex.org/W2997419692","https://openalex.org/W3007328579","https://openalex.org/W3008283340","https://openalex.org/W3015199127","https://openalex.org/W3016031604","https://openalex.org/W3016232124","https://openalex.org/W3016400019","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3027008958","https://openalex.org/W3097643313","https://openalex.org/W3099330747","https://openalex.org/W3105031100","https://openalex.org/W3143843080","https://openalex.org/W3151596526","https://openalex.org/W3162347631","https://openalex.org/W6633191483","https://openalex.org/W6678809451","https://openalex.org/W6728841359","https://openalex.org/W6765757276","https://openalex.org/W6777776875","https://openalex.org/W6782161367","https://openalex.org/W6784351597"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W1521049138","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1999004162","https://openalex.org/W4280634406"],"abstract_inverted_index":{"Multi-speaker":[0],"speech":[1,24,30,114],"recognition":[2,31,73],"of":[3,82,89,112,126,138,145],"unsegmented":[4],"recordings":[5],"has":[6,38],"diverse":[7],"applications":[8],"such":[9],"as":[10,102,104],"meeting":[11,64],"transcription":[12],"and":[13,28,72,92,100,117],"automatic":[14,29],"subtitle":[15],"generation.":[16],"With":[17],"technical":[18],"advances":[19],"in":[20,33,75],"systems":[21],"dealing":[22],"with":[23,123],"separation,":[25,70],"speaker":[26],"diarization,":[27,71],"(ASR)":[32],"the":[34,62,80,90,110,124],"last":[35],"decade,":[36],"it":[37],"become":[39],"possible":[40],"to":[41,143],"build":[42],"pipelines":[43],"that":[44,76,109,144],"achieve":[45],"reasonable":[46],"error":[47],"rates":[48],"on":[49],"this":[50,53],"task.":[51],"In":[52],"paper,":[54],"we":[55],"propose":[56],"an":[57],"end-to-end":[58],"modular":[59],"system":[60,133],"for":[61,115],"LibriCSS":[63],"data,":[65],"which":[66,140],"combines":[67],"independently":[68],"trained":[69],"components,":[74],"order.":[77],"We":[78],"study":[79],"effect":[81],"different":[83],"state-of-the-art":[84],"methods":[85],"at":[86],"each":[87],"stage":[88],"pipeline,":[91],"report":[93],"results":[94],"using":[95],"task-specific":[96],"metrics":[97],"like":[98],"SDR":[99],"DER,":[101],"well":[103],"downstream":[105],"WER.":[106],"Experiments":[107],"indicate":[108],"problem":[111],"overlapping":[113],"diarization":[116],"ASR":[118],"can":[119],"be":[120],"effectively":[121],"mitigated":[122],"presence":[125],"a":[127,135,146],"well-trained":[128],"separation":[129],"module.":[130],"Our":[131],"best":[132],"achieves":[134],"speaker-attributed":[136],"WER":[137],"12.7%,":[139],"is":[141],"close":[142],"non-overlapping":[147],"ASR.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":17},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
