{"id":"https://openalex.org/W4283707580","doi":"https://doi.org/10.21437/interspeech.2022-877","title":"TALCS: An open-source Mandarin-English code-switching corpus and a speech recognition baseline","display_name":"TALCS: An open-source Mandarin-English code-switching corpus and a speech recognition baseline","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283707580","doi":"https://doi.org/10.21437/interspeech.2022-877"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-877","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-877","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5000406335","display_name":"Chengfei Li","orcid":"https://orcid.org/0000-0002-1356-7466"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chengfei Li","raw_affiliation_strings":["TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069695280","display_name":"Shuhao Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuhao Deng","raw_affiliation_strings":["TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102819501","display_name":"Yao-Ping Wang","orcid":"https://orcid.org/0000-0003-0994-6030"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaoping Wang","raw_affiliation_strings":["TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083819169","display_name":"Guangjing Wang","orcid":"https://orcid.org/0000-0002-9353-9042"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guangjing Wang","raw_affiliation_strings":["TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012489033","display_name":"Yaguang Gong","orcid":"https://orcid.org/0009-0009-6502-9262"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaguang Gong","raw_affiliation_strings":["TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012302243","display_name":"Changbin Chen","orcid":"https://orcid.org/0000-0002-7961-3488"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changbin Chen","raw_affiliation_strings":["TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036032938","display_name":"Jinfeng Bai","orcid":"https://orcid.org/0000-0001-8940-480X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinfeng Bai","raw_affiliation_strings":["TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5000406335"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2487,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81306901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9951000213623047,"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":0.9677000045776367,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8149470090866089},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7445762157440186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7303441762924194},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6591367125511169},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.48706749081611633},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.429697185754776},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.421917200088501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34249424934387207},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17757800221443176},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14676186442375183},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.06390783190727234},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.04562234878540039}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8149470090866089},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7445762157440186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7303441762924194},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6591367125511169},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.48706749081611633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.429697185754776},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.421917200088501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34249424934387207},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17757800221443176},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14676186442375183},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.06390783190727234},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.04562234878540039},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-877","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-877","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W2094655846","https://openalex.org/W2102113734","https://openalex.org/W2153433699","https://openalex.org/W2160815625","https://openalex.org/W2345986601","https://openalex.org/W2791281350","https://openalex.org/W2891616026","https://openalex.org/W2896068220","https://openalex.org/W2899073901","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2972324550","https://openalex.org/W2981413347","https://openalex.org/W3042170933","https://openalex.org/W3095307127","https://openalex.org/W3097777922","https://openalex.org/W3197478142","https://openalex.org/W4291566970","https://openalex.org/W4307106469","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2189064394","https://openalex.org/W2347798153","https://openalex.org/W3107474891","https://openalex.org/W2435130738","https://openalex.org/W2755682845","https://openalex.org/W4283707580","https://openalex.org/W1517743118","https://openalex.org/W1880637544","https://openalex.org/W4312706664","https://openalex.org/W2003625507"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,113],"new":[4],"corpus":[5,21,50,83,87],"of":[6,40,142],"Mandarin-English":[7,56],"code-switching":[8,17,57],"speech":[9,18,41,61,108,128],"recognition-TALCS":[10],"corpus,":[11,100],"suitable":[12],"for":[13,91],"training":[14],"and":[15,82,118,145,149],"evaluating":[16],"recognition":[19,62,109,129],"systems.TALCS":[20],"is":[22,51,88,131,153],"derived":[23],"from":[24],"real":[25],"online":[26],"one-to-one":[27],"English":[28],"teaching":[29],"scenes":[30],"in":[31,65,76,105,125,133],"TAL":[32],"education":[33],"group,":[34],"which":[35],"contains":[36],"roughly":[37],"587":[38],"hours":[39],"sampled":[42],"at":[43],"16":[44],"kHz.To":[45],"our":[46],"best":[47],"knowledge,":[48],"TALCS":[49,86,99,134],"the":[52,66,73,85,94,126,140,150],"largest":[53],"well":[54],"labeled":[55],"open":[58],"source":[59],"automatic":[60],"(ASR)":[63],"dataset":[64],"world.In":[67],"this":[68],"paper,":[69],"we":[70,101],"will":[71],"introduce":[72],"recording":[74],"procedure":[75],"detail,":[77],"including":[78,116],"audio":[79,143],"capturing":[80],"devices":[81],"environments.And":[84],"freely":[89],"available":[90],"download":[92],"under":[93],"permissive":[95],"license":[96],"1":[97],".Using":[98],"conduct":[102],"ASR":[103],"experiments":[104],"two":[106,127],"popular":[107],"toolkits":[110,130],"to":[111],"make":[112],"baseline":[114,151],"system,":[115],"ESPnet":[117],"Wenet.The":[119],"Mixture":[120],"Error":[121],"Rate":[122],"(MER)":[123],"performance":[124],"compared":[132],"corpus.The":[135],"experimental":[136],"results":[137],"implies":[138],"that":[139],"quality":[141],"recordings":[144],"transcriptions":[146],"are":[147],"promising":[148],"system":[152],"workable.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
