{"id":"https://openalex.org/W2787311093","doi":"https://doi.org/10.1109/apsipa.2017.8282279","title":"Improving N-gram language modeling for code-switching speech recognition","display_name":"Improving N-gram language modeling for code-switching speech recognition","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787311093","doi":"https://doi.org/10.1109/apsipa.2017.8282279","mag":"2787311093"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5034445480","display_name":"Zhiping Zeng","orcid":"https://orcid.org/0000-0002-6315-4408"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiping Zeng","raw_affiliation_strings":["School of Communication & Information Engineering, Shanghai University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Communication & Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"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":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001136890","display_name":"Tze Yuang Chong","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":"Tze Yuang Chong","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","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":["Nanyang Technological University, Singapore, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore, SG","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5034445480"],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":null,"apc_paid":null,"fwci":2.5353,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.92082186,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"3","issue":null,"first_page":"1596","last_page":"1601"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","score":0.9943000078201294,"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/perplexity","display_name":"Perplexity","score":0.9823716282844543},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.8654605746269226},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.8362903594970703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8160793781280518},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.6979347467422485},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6096372008323669},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6094846725463867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5836961269378662},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5426668524742126},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.5308018326759338},{"id":"https://openalex.org/keywords/word-lists-by-frequency","display_name":"Word lists by frequency","score":0.4372757077217102},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4312286078929901},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2527658939361572},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.18817463517189026},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16468337178230286},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.13952136039733887}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9823716282844543},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.8654605746269226},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.8362903594970703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8160793781280518},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.6979347467422485},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6096372008323669},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6094846725463867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5836961269378662},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5426668524742126},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.5308018326759338},{"id":"https://openalex.org/C175293574","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word lists by frequency","level":3,"score":0.4372757077217102},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4312286078929901},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2527658939361572},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.18817463517189026},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16468337178230286},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.13952136039733887},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"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/apsipa.2017.8282279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W197277712","https://openalex.org/W761725120","https://openalex.org/W1488377236","https://openalex.org/W1608515068","https://openalex.org/W1876715006","https://openalex.org/W2009957195","https://openalex.org/W2038116248","https://openalex.org/W2042655742","https://openalex.org/W2043762869","https://openalex.org/W2079623482","https://openalex.org/W2084500694","https://openalex.org/W2094655846","https://openalex.org/W2098355803","https://openalex.org/W2119659342","https://openalex.org/W2121227244","https://openalex.org/W2130254740","https://openalex.org/W2136542423","https://openalex.org/W2251232800","https://openalex.org/W2252095989","https://openalex.org/W2296354688","https://openalex.org/W2345986601","https://openalex.org/W2402146185","https://openalex.org/W2407467516","https://openalex.org/W2507287275","https://openalex.org/W2514741789","https://openalex.org/W2530571334","https://openalex.org/W2571803900","https://openalex.org/W2976852125","https://openalex.org/W3098911752","https://openalex.org/W4240913316","https://openalex.org/W6603616073","https://openalex.org/W6622259991","https://openalex.org/W6629199099","https://openalex.org/W6661081679","https://openalex.org/W6678277124","https://openalex.org/W6691537765","https://openalex.org/W6697366141","https://openalex.org/W6712930963","https://openalex.org/W6714159922","https://openalex.org/W6731987800"],"related_works":["https://openalex.org/W2053242504","https://openalex.org/W1903115690","https://openalex.org/W2397861987","https://openalex.org/W2126623367","https://openalex.org/W1495755158","https://openalex.org/W1577263324","https://openalex.org/W2787311093","https://openalex.org/W2950575438","https://openalex.org/W2105076537","https://openalex.org/W2169518243"],"abstract_inverted_index":{"Code-switching":[0],"language":[1,18,37,82,90,104,128,135,144,175,185],"modeling":[2,38,105,186],"is":[3],"challenging":[4],"due":[5],"to":[6,140,178,188],"statistics":[7,15],"of":[8,16,26,40,62,74,92,182],"each":[9],"individual":[10],"language,":[11],"as":[12,14,53,84,86],"well":[13,85],"cross-lingual":[17],"are":[19,45,51,97,169],"insufficient.":[20],"To":[21],"compensate":[22],"for":[23],"the":[24,60,63,78,87,99,125,131,172,180,183],"issue":[25],"statistical":[27],"insufficiency,":[28],"in":[29,72],"this":[30],"paper":[31],"we":[32,118,192],"propose":[33],"a":[34],"word-class":[35,88,101,133,142],"n-gram":[36,81,89,127,134,143,174],"approach":[39,106,187],"which":[41,93],"only":[42],"infrequent":[43],"words":[44,50,96],"clustered":[46],"while":[47],"most":[48],"frequent":[49],"treated":[52],"singleton":[54],"classes":[55],"themselves.":[56],"We":[57,137],"first":[58],"demonstrate":[59],"effectiveness":[61],"proposed":[64,100,132,152,184],"method":[65],"on":[66,111,161],"our":[67,112,151,162],"English-Mandarin":[68],"code-switching":[69,189],"SEAME":[70,113,163],"data":[71,115,149,165],"terms":[73],"perplexity.":[75],"Compared":[76],"with":[77,130,150,171],"conventional":[79],"word":[80,126,173],"models,":[83],"models":[91,129,145],"entire":[94],"vocabulary":[95],"clustered,":[98],"n-":[102],"gram":[103],"can":[107],"yield":[108],"lower":[109],"perplexity":[110,121,156],"dev":[114,164],"sets.":[116],"Additionally,":[117],"observed":[119],"further":[120],"reduction":[122],"by":[123],"interpolating":[124],"models.":[136,176],"also":[138],"attempted":[139],"build":[141],"using":[146],"third-party":[147],"text":[148],"method,":[153],"and":[154],"similar":[155],"performance":[157],"improvement":[158],"was":[159],"obtained":[160],"sets":[166],"when":[167],"they":[168],"interpolated":[170],"Finally,":[177],"examine":[179],"contribution":[181],"speech":[190],"recognition,":[191],"conducted":[193],"lattice":[194],"based":[195],"n-best":[196],"rescoring.":[197]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}