{"id":"https://openalex.org/W3095307127","doi":"https://doi.org/10.21437/interspeech.2020-1582","title":"Monolingual Data Selection Analysis for English-Mandarin Hybrid Code-Switching Speech Recognition","display_name":"Monolingual Data Selection Analysis for English-Mandarin Hybrid Code-Switching Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095307127","doi":"https://doi.org/10.21437/interspeech.2020-1582","mag":"3095307127"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1582","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5100753683","display_name":"Haobo Zhang","orcid":"https://orcid.org/0009-0001-0670-1786"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobo Zhang","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039696635","display_name":"Haihua Xu","orcid":"https://orcid.org/0000-0002-2220-8465"},"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":"Haihua Xu","raw_affiliation_strings":["Temasek Laboratories, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046222772","display_name":"Van Tung Pham","orcid":"https://orcid.org/0000-0002-2103-1901"},"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":"Van Tung Pham","raw_affiliation_strings":["Temasek Laboratories, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Laboratories, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101667364","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0002-9131-5854"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Huang","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"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":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore","Temasek Laboratories, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Temasek Laboratories, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101667364"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.46,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6567518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2392","last_page":"2396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"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":0.9966999888420105,"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":0.9542999863624573,"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/T10860","display_name":"Speech and Audio Processing","score":0.9534000158309937,"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":0.8188390731811523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7878695130348206},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.7238666415214539},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6622403264045715},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6523528099060059},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5083085894584656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4185590445995331},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4174681305885315},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22018897533416748},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15135443210601807}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8188390731811523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878695130348206},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.7238666415214539},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6622403264045715},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6523528099060059},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5083085894584656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4185590445995331},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4174681305885315},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22018897533416748},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15135443210601807},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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.2020-1582","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320331617","display_name":"National Supercomputing Centre Singapore","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1984985727","https://openalex.org/W2053625667","https://openalex.org/W2062227835","https://openalex.org/W2079623482","https://openalex.org/W2135241496","https://openalex.org/W2399016933","https://openalex.org/W2400997536","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2799800213","https://openalex.org/W2883989418","https://openalex.org/W2888867175","https://openalex.org/W2926989360","https://openalex.org/W2939757332","https://openalex.org/W2963292011","https://openalex.org/W2963850025","https://openalex.org/W2964156075","https://openalex.org/W2964309797","https://openalex.org/W2972417954","https://openalex.org/W2972818416","https://openalex.org/W3008525923"],"related_works":["https://openalex.org/W2374317326","https://openalex.org/W2990005675","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,76,127],"conduct":[4],"data":[5,37,45,49,61,67,78,82,96,100,119,134],"selection":[6,68],"analysis":[7],"in":[8,26,90],"building":[9],"an":[10,39],"English-Mandarin":[11],"code-switching":[12,48,92,163],"(CS)":[13],"speech":[14],"recognition":[15],"(CSSR)":[16],"system,":[17,124],"which":[18,116],"is":[19,56,70,80,83,97,111],"aimed":[20],"for":[21],"a":[22,35,43,112,137,156],"real":[23],"CSSR":[24,123,138,145],"contest":[25],"China.The":[27],"overall":[28,60],"training":[29],"sets":[30],"have":[31],"three":[32],"subsets,":[33],"i.e.,":[34],"codeswitching":[36],"set,":[38],"English":[40,95],"(LibriSpeech)":[41],"and":[42,65],"Mandarin":[44,51,88,99],"set":[46],"respectively.The":[47],"are":[50,107],"dominated.First":[52],"of":[53,131],"all,":[54],"it":[55,153],"found":[57],"using":[58],"the":[59,87,91,122,129,141,159],"yields":[62],"worse":[63],"results,":[64],"hence":[66],"study":[69],"necessary.Then":[71],"to":[72,135],"exploit":[73],"monolingual":[74,118,133],"data,":[75,93],"find":[77],"matching":[79],"crucial.Mandarin":[81],"closely":[84],"matched":[85],"with":[86,140,158],"part":[89],"while":[94],"not.However,":[98],"only":[101],"helps":[102],"on":[103,162],"those":[104],"utterances":[105],"that":[106],"significantly":[108],"Mandarin-dominated.Besides,":[109],"there":[110],"balance":[113],"point,":[114],"over":[115],"more":[117],"will":[120],"divert":[121],"degrading":[125],"results.Finally,":[126],"analyze":[128],"effectiveness":[130],"combining":[132],"train":[136],"system":[139,146],"HMM-DNN":[142],"hybrid":[143],"framework.The":[144],"can":[147],"perform":[148],"within-utterance":[149],"code-switch":[150],"recognition,":[151],"but":[152],"still":[154],"has":[155],"margin":[157],"one":[160],"trained":[161],"data.":[164]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}