{"id":"https://openalex.org/W3197380209","doi":"https://doi.org/10.21437/interspeech.2021-82","title":"End-to-End Language Diarization for Bilingual Code-Switching Speech","display_name":"End-to-End Language Diarization for Bilingual Code-Switching Speech","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197380209","doi":"https://doi.org/10.21437/interspeech.2021-82","mag":"3197380209"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-82","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-82","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5091096053","display_name":"Hexin Liu","orcid":"https://orcid.org/0000-0002-3998-9229"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Hexin Liu","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Leibny Paola Garc\u00eda Perera","raw_affiliation_strings":["Delft University of Technology"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381540","display_name":"Xinyi Zhang","orcid":"https://orcid.org/0000-0001-9924-3990"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xinyi Zhang","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082613025","display_name":"Justin Dauwels","orcid":"https://orcid.org/0000-0002-4390-1568"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Justin Dauwels","raw_affiliation_strings":["Department of Microelectronics, Delft University of Technology, Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Microelectronics, Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010202250","display_name":"Andy W. H. Khong","orcid":"https://orcid.org/0000-0002-0708-4791"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Andy W.H. Khong","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"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":"Sanjeev Khudanpur","raw_affiliation_strings":["CLSP and HLT-COE, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"CLSP and HLT-COE, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072241540","display_name":"Suzy J Styles","orcid":"https://orcid.org/0000-0003-3517-9680"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Suzy J. Styles","raw_affiliation_strings":["Psychology, School of Social Sciences, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Psychology, School of Social Sciences, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5091096053"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":2.6593,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91633622,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1489","last_page":"1493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.7507071495056152},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7327902317047119},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6097304821014404},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48743394017219543},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4223962128162384},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3967205584049225},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.31996679306030273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28143781423568726},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.14040344953536987}],"concepts":[{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.7507071495056152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7327902317047119},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6097304821014404},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48743394017219543},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4223962128162384},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3967205584049225},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31996679306030273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28143781423568726},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.14040344953536987},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-82","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-82","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:e80e9a22-0008-4684-8676-c67d0518b2d6","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:e80e9a22-0008-4684-8676-c67d0518b2d6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2235879186","display_name":null,"funder_award_id":"NRF2016-SOL002-011","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G277544474","display_name":null,"funder_award_id":"NRF2016","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G3921862303","display_name":null,"funder_award_id":"JHU IO 90071537","funder_id":"https://openalex.org/F4320320766","funder_display_name":"Nanyang Technological University"},{"id":"https://openalex.org/G4267629283","display_name":null,"funder_award_id":"NRF2016-SOL002-011","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G4598980868","display_name":null,"funder_award_id":"NRF2016_SOL002","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W48568691","https://openalex.org/W197277712","https://openalex.org/W1522301498","https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2049032416","https://openalex.org/W2079735306","https://openalex.org/W2104457544","https://openalex.org/W2150769028","https://openalex.org/W2193413348","https://openalex.org/W2221409856","https://openalex.org/W2408021097","https://openalex.org/W2638067502","https://openalex.org/W2807627734","https://openalex.org/W2889381673","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2902094805","https://openalex.org/W2962788262","https://openalex.org/W2963032538","https://openalex.org/W2963403868","https://openalex.org/W2963470929","https://openalex.org/W2964121744","https://openalex.org/W2972433488","https://openalex.org/W2972808922","https://openalex.org/W2972949456","https://openalex.org/W2973072991","https://openalex.org/W3008357631","https://openalex.org/W3123196343","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W2111874347","https://openalex.org/W1521049138","https://openalex.org/W1509309911","https://openalex.org/W3120512183","https://openalex.org/W2096510939","https://openalex.org/W2041797852","https://openalex.org/W2160753975","https://openalex.org/W1940231550"],"abstract_inverted_index":{"<p>We":[0],"propose":[1],"two":[2],"end-to-end":[3],"neural":[4],"configurations":[5],"for":[6],"language":[7,81],"diarization":[8],"on":[9,51,88,132,158],"bilingual":[10],"code-switching":[11],"speech.":[12],"The":[13,44,60],"first,":[14],"a":[15,19,57,77,118,128,154],"BLSTM-E2E":[16],"architecture,":[17,48],"includes":[18],"set":[20],"of":[21,37,79,121,151,156],"stacked":[22],"bidirectional":[23],"LSTMs":[24],"to":[25,34,40,75],"compute":[26],"embeddings":[27,67,74],"and":[28,100,127],"incorporates":[29],"the":[30,41,69,85,89,93,106,136,140,159,164],"deep":[31],"clustering":[32],"loss":[33],"enforce":[35],"grouping":[36],"languages":[38],"belonging":[39],"same":[42],"class.":[43],"second,":[45],"an":[46,52,149],"XSA-E2E":[47,115,146],"is":[49],"based":[50],"x-vector":[53],"model":[54],"followed":[55],"by":[56],"self-attention":[58],"encoder.":[59],"former":[61],"encodes":[62],"frame-level":[63],"features":[64],"into":[65],"segmentlevel":[66],"while":[68],"latter":[70],"considers":[71],"all":[72],"those":[73],"generate":[76],"sequence":[78],"segment-level":[80],"labels.":[82],"We":[83],"evaluated":[84],"proposed":[86,114,145],"methods":[87],"dataset":[90],"obtained":[91],"from":[92,105,163],"shared":[94],"task":[95],"B":[96],"in":[97,123,139],"WSTCSMC":[98,141],"2020":[99,142],"our":[101,113],"handcrafted":[102],"simulated":[103,160],"data":[104,161],"SEAME":[107,165],"dataset.":[108,143,166],"Experimental":[109],"results":[110],"show":[111],"that":[112],"architecture":[116,147],"achieved":[117,148],"relative":[119,130],"improvement":[120,131],"12.1%":[122],"equal":[124],"error":[125],"rate":[126],"7.4%":[129],"accuracy":[133,150],"compared":[134],"with":[135,153],"baseline":[137,155],"algorithm":[138],"Our":[144],"89.84%":[152],"85.60%":[157],"derived":[162],"</p>":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}