{"id":"https://openalex.org/W4385822988","doi":"https://doi.org/10.21437/interspeech.2023-1446","title":"MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization","display_name":"MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822988","doi":"https://doi.org/10.21437/interspeech.2023-1446"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1446","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.tudelft.nl/file/File_c2e30fd4-9d70-451c-9f2d-875addaf04ef","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010820511","display_name":"Yi Han Victoria Chua","orcid":"https://orcid.org/0000-0002-0755-3148"},"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":"Victoria Y. H. Chua","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"]}]},{"author_position":"middle","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":false,"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 Garcia","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/A5008363712","display_name":"Fei Ting Woon","orcid":null},"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":"Fei Ting Woon","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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112926904","display_name":"Jinyi Wong","orcid":null},"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":"Jinyi Wong","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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362465","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0000-0003-2138-4608"},"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":"Xiangyu Zhang","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":"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":"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/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":"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":10,"corresponding_author_ids":["https://openalex.org/A5010820511"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":1.9427,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88846575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4109","last_page":"4113"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9940000176429749,"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":0.9896000027656555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8418323993682861},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5831615924835205},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.55597323179245},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5553367733955383},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5293396711349487},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.4773254990577698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.446199893951416},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4400312006473541},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4345618188381195},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24891984462738037},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.18526044487953186},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.16505485773086548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8418323993682861},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5831615924835205},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.55597323179245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5553367733955383},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5293396711349487},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.4773254990577698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.446199893951416},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4400312006473541},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4345618188381195},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24891984462738037},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.18526044487953186},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.16505485773086548},{"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.2023-1446","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:73006d56-c470-4390-8c12-f2725d5ecbf9","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:73006d56-c470-4390-8c12-f2725d5ecbf9","pdf_url":"https://repository.tudelft.nl/file/File_c2e30fd4-9d70-451c-9f2d-875addaf04ef","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:73006d56-c470-4390-8c12-f2725d5ecbf9","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:73006d56-c470-4390-8c12-f2725d5ecbf9","pdf_url":"https://repository.tudelft.nl/file/File_c2e30fd4-9d70-451c-9f2d-875addaf04ef","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"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/G2898130230","display_name":null,"funder_award_id":"120435","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"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"},{"id":"https://openalex.org/G5877145623","display_name":null,"funder_award_id":"2120435","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385822988.pdf","grobid_xml":"https://content.openalex.org/works/W4385822988.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2044707576","https://openalex.org/W2079041169","https://openalex.org/W2222917927","https://openalex.org/W2884797218","https://openalex.org/W2888924726","https://openalex.org/W2972449503","https://openalex.org/W2974231335","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3043914263","https://openalex.org/W3045733287","https://openalex.org/W3146772526","https://openalex.org/W3197380209","https://openalex.org/W3205878676","https://openalex.org/W4221141648","https://openalex.org/W4221158519","https://openalex.org/W4231234721","https://openalex.org/W4283069819","https://openalex.org/W4292968575","https://openalex.org/W4295682935","https://openalex.org/W4296068794","https://openalex.org/W4296069321","https://openalex.org/W4297841366","https://openalex.org/W4311000453","https://openalex.org/W4375869049","https://openalex.org/W4379087139","https://openalex.org/W4379087924","https://openalex.org/W4385807507","https://openalex.org/W4385823049","https://openalex.org/W4385823349"],"related_works":["https://openalex.org/W113515668","https://openalex.org/W2154680756","https://openalex.org/W2155576284","https://openalex.org/W2068512280","https://openalex.org/W1587721369","https://openalex.org/W2550534525","https://openalex.org/W4214593397","https://openalex.org/W1833998246","https://openalex.org/W2007071873","https://openalex.org/W175497273"],"abstract_inverted_index":{"<p>To":[0],"enhance":[1],"the":[2,43,105,122,127],"reliability":[3],"and":[4,10,18,38,82,111,117],"robustness":[5],"of":[6,54,59,99],"language":[7,11,36],"identification":[8],"(LID)":[9],"diarization":[12],"(LD)":[13],"systems":[14,119],"for":[15,24,114],"heterogeneous":[16],"populations":[17],"scenarios,":[19],"there":[20],"is":[21],"a":[22,48,72,97],"need":[23],"speech":[25,39,87],"processing":[26],"models":[27],"to":[28,121],"be":[29],"trained":[30],"on":[31],"datasets":[32],"that":[33],"feature":[34],"diverse":[35,92],"registers":[37],"patterns.":[40],"We":[41],"present":[42],"MERLIon":[44,123],"CCS":[45,124],"challenge,":[46],"featuring":[47],"first-of-its-kind":[49],"Zoom":[50],"video":[51],"call":[52],"dataset":[53],"parent-child":[55],"shared":[56],"book":[57],"reading,":[58],"over":[60,64],"30":[61],"hours":[62],"with":[63,91],"300":[65],"recordings,":[66],"annotated":[67],"by":[68],"multilingual":[69],"transcribers":[70],"using":[71,126],"high-fidelity":[73],"linguistic":[74],"transcription":[75],"protocol.":[76],"The":[77],"audio":[78],"corpus":[79],"features":[80],"spontaneous":[81],"in-the-wild":[83],"English-Mandarin":[84],"code-switching,":[85],"child-directed":[86],"in":[88,96],"non-standard":[89],"accents":[90],"language-mixing":[93],"patterns":[94],"recorded":[95],"variety":[98],"home":[100],"environments.":[101],"This":[102],"report":[103],"describes":[104],"corpus,":[106],"as":[107,109],"well":[108],"LID":[110],"LD":[112],"results":[113],"our":[115],"baseline":[116],"several":[118],"submitted":[120],"challenge":[125],"corpus.</p>":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}