{"id":"https://openalex.org/W1977560964","doi":"https://doi.org/10.1109/iscslp.2010.5684900","title":"Semantics-based language modeling for Cantonese-English code-mixing speech recognition","display_name":"Semantics-based language modeling for Cantonese-English code-mixing speech recognition","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W1977560964","doi":"https://doi.org/10.1109/iscslp.2010.5684900","mag":"1977560964"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","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/A5102992790","display_name":"Houwei Cao","orcid":"https://orcid.org/0000-0002-2310-7682"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Houwei Cao","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong, China","Department of Electronic Engineering, The Chinese University of Hong Hong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Hong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062365583","display_name":"P.C. Ching","orcid":"https://orcid.org/0000-0002-4692-8707"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"P. C. Ching","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong, China","Department of Electronic Engineering, The Chinese University of Hong Hong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Hong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong, China","Department of Electronic Engineering, The Chinese University of Hong Hong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Hong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083831776","display_name":"Yu Ting Yeung","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yu Ting Yeung","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong, China","Department of Electronic Engineering, The Chinese University of Hong Hong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Hong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.4663,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.72055121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"246","last_page":"250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955000281333923,"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":0.9760000109672546,"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/perplexity","display_name":"Perplexity","score":0.9149930477142334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8500649929046631},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7233588695526123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6281282901763916},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.611880362033844},{"id":"https://openalex.org/keywords/code-mixing","display_name":"Code-mixing","score":0.5370982885360718},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.49884843826293945},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4731498956680298},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4345742464065552},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4208022654056549},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.24203798174858093},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22947368025779724},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1260037124156952},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.08394995331764221}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9149930477142334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500649929046631},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7233588695526123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6281282901763916},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.611880362033844},{"id":"https://openalex.org/C2778598016","wikidata":"https://www.wikidata.org/wiki/Q3201279","display_name":"Code-mixing","level":3,"score":0.5370982885360718},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.49884843826293945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4731498956680298},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4345742464065552},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4208022654056549},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.24203798174858093},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22947368025779724},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1260037124156952},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08394995331764221},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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:10.1109/iscslp.2010.5684900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W99394049","https://openalex.org/W121747529","https://openalex.org/W656085213","https://openalex.org/W2024490156","https://openalex.org/W2100506586","https://openalex.org/W2107201284","https://openalex.org/W2134817403","https://openalex.org/W2161490380","https://openalex.org/W2499636221","https://openalex.org/W4235505822","https://openalex.org/W6604978991","https://openalex.org/W6680125536"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2084531783","https://openalex.org/W2902731467","https://openalex.org/W2020757772"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,19,39,52,75,81,85,106,114,116,122,124,131,153,168],"problem":[4],"of":[5,10,21,24,41,80,102,108],"language":[6,89,125,136],"modeling":[7],"for":[8,167],"LVCSR":[9],"Cantonese-English":[11],"code-mixing":[12,25,175],"utterances":[13],"spoken":[14],"in":[15,84,100,105,174],"daily":[16],"communications.":[17],"In":[18,48,66],"absence":[20],"sufficient":[22],"amount":[23],"text":[26],"data,":[27],"translation-based":[28,49],"and":[29,43,77,104,164,171],"semantics-based":[30,67,88],"mapping":[31,50,68,71,95],"are":[32,91,98,150],"applied":[33],"on":[34,74,141,144],"n-grams":[35,46,62,119],"to":[36,58,63],"better":[37,123],"estimate":[38],"probability":[40],"low-frequency":[42],"unseen":[44],"mixed-language":[45,64,118],"events.":[47],"scheme,":[51,69],"Cantonese-to-English":[53],"translation":[54],"dictionary":[55],"is":[56,72,162],"adopted":[57],"transcribe":[59],"monolingual":[60],"Cantonese":[61,172],"n-grams.":[65],"n-gram":[70],"based":[73],"meaning":[76],"syntactic":[78],"function":[79],"English":[82,146,169],"words":[83,147,170],"lexicon.":[86],"Different":[87],"models":[90,137],"trained":[92],"with":[93,152],"different":[94],"schemes.":[96],"They":[97],"evaluated":[99],"terms":[101],"perplexity":[103,127],"task":[107],"LVCSR.":[109],"Experimental":[110],"results":[111],"confirm":[112],"that,":[113],"more":[115],"observed":[117],"after":[120],"mapping,":[121],"model":[126],"as":[128,130],"well":[129],"recognition":[132,142,159],"performance.":[133],"The":[134,157],"proposed":[135],"show":[138],"significant":[139],"improvement":[140],"performance":[143],"embedded":[145],"when":[148],"they":[149],"compared":[151],"baseline":[154],"3-gram":[155],"LM.":[156],"best":[158],"accuracy":[160],"attained":[161],"63.9%":[163],"74.7%":[165],"respectively":[166],"characters":[173],"utterances.":[176]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}