{"id":"https://openalex.org/W3117353267","doi":"https://doi.org/10.1109/o-cocosda50338.2020.9295036","title":"Enhancing Large Vocabulary Continuous Speech Recognition System for Urdu-English Conversational Code-Switched Speech","display_name":"Enhancing Large Vocabulary Continuous Speech Recognition System for Urdu-English Conversational Code-Switched Speech","publication_year":2020,"publication_date":"2020-11-05","ids":{"openalex":"https://openalex.org/W3117353267","doi":"https://doi.org/10.1109/o-cocosda50338.2020.9295036","mag":"3117353267"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda50338.2020.9295036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda50338.2020.9295036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5032869520","display_name":"Muhammad Umar Farooq","orcid":"https://orcid.org/0000-0002-6610-0923"},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]},{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]}],"countries":["PK","PL"],"is_corresponding":false,"raw_author_name":"Muhammad Umar Farooq","raw_affiliation_strings":["Center for Language Engineering, Al-Khawarizmi Institute of Computer Science, University of Engineering and Technology, Lahore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language Engineering, Al-Khawarizmi Institute of Computer Science, University of Engineering and Technology, Lahore","institution_ids":["https://openalex.org/I142732210","https://openalex.org/I4210087266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034131804","display_name":"Farah Adeeba","orcid":null},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]},{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]}],"countries":["PK","PL"],"is_corresponding":false,"raw_author_name":"Farah Adeeba","raw_affiliation_strings":["Center for Language Engineering, Al-Khawarizmi Institute of Computer Science, University of Engineering and Technology, Lahore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language Engineering, Al-Khawarizmi Institute of Computer Science, University of Engineering and Technology, Lahore","institution_ids":["https://openalex.org/I142732210","https://openalex.org/I4210087266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033831523","display_name":"Sarmad Hussain","orcid":"https://orcid.org/0000-0001-6956-745X"},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]},{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]}],"countries":["PK","PL"],"is_corresponding":false,"raw_author_name":"Sarmad Hussain","raw_affiliation_strings":["Center for Language Engineering, Al-Khawarizmi Institute of Computer Science, University of Engineering and Technology, Lahore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language Engineering, Al-Khawarizmi Institute of Computer Science, University of Engineering and Technology, Lahore","institution_ids":["https://openalex.org/I142732210","https://openalex.org/I4210087266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018363969","display_name":"Sahar Rauf","orcid":"https://orcid.org/0000-0002-8585-0754"},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]},{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]}],"countries":["PK","PL"],"is_corresponding":false,"raw_author_name":"Sahar Rauf","raw_affiliation_strings":["Center for Language Engineering, Al-Khawarizmi Institute of Computer Science, University of Engineering and Technology, Lahore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language Engineering, Al-Khawarizmi Institute of Computer Science, University of Engineering and Technology, Lahore","institution_ids":["https://openalex.org/I142732210","https://openalex.org/I4210087266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112928053","display_name":"Maryam Khalid","orcid":null},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]},{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]}],"countries":["PK","PL"],"is_corresponding":false,"raw_author_name":"Maryam Khalid","raw_affiliation_strings":["Center for Language Engineering, Al-Khawarizmi Institute of Computer Science, University of Engineering and Technology, Lahore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language Engineering, Al-Khawarizmi Institute of Computer Science, University of Engineering and Technology, Lahore","institution_ids":["https://openalex.org/I142732210","https://openalex.org/I4210087266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1354,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58897401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"155","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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":0.9883000254631042,"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/urdu","display_name":"Urdu","score":0.917094349861145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8168054223060608},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6762456297874451},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6720690131187439},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6351947784423828},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5709933042526245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5223109126091003},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4639105200767517},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45893996953964233},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45257964730262756},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.438334584236145},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4272107183933258},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20947161316871643}],"concepts":[{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.917094349861145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8168054223060608},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6762456297874451},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6720690131187439},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6351947784423828},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5709933042526245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5223109126091003},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4639105200767517},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45893996953964233},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45257964730262756},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.438334584236145},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4272107183933258},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20947161316871643},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda50338.2020.9295036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda50338.2020.9295036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"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":26,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W2039387825","https://openalex.org/W2147550046","https://openalex.org/W2514741789","https://openalex.org/W2587496545","https://openalex.org/W2610844179","https://openalex.org/W2611043340","https://openalex.org/W2749874290","https://openalex.org/W2806311807","https://openalex.org/W2888790405","https://openalex.org/W2889282842","https://openalex.org/W2972312617","https://openalex.org/W2972354933","https://openalex.org/W2972417954","https://openalex.org/W2972451902","https://openalex.org/W2972470300","https://openalex.org/W2972808286","https://openalex.org/W2972888990","https://openalex.org/W2973132572","https://openalex.org/W2973166416","https://openalex.org/W2973215447","https://openalex.org/W3143136364","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6751793521"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340","https://openalex.org/W2145230572"],"abstract_inverted_index":{"This":[0,95],"paper":[1],"presents":[2],"first":[3],"step":[4],"towards":[5],"Large":[6],"Vocabulary":[7],"Continuous":[8],"Speech":[9],"Recognition":[10],"(LVCSR)":[11],"system":[12,129],"for":[13,84],"Urdu-English":[14,58],"code-switched":[15,59,93],"conversational":[16],"speech.":[17,94],"Urdu":[18,47,74,89,114],"is":[19,38,79,98,138,165],"the":[20,35,128],"national":[21],"language":[22,40,151],"and":[23,43,105,120,145],"lingua":[24],"franca":[25],"of":[26,41,86,103,108,113],"Pakistan,":[27],"with":[28,46],"100":[29],"million":[30],"speakers":[31],"worldwide.":[32],"English,":[33],"on":[34,171],"other":[36],"hand,":[37],"official":[39],"Pakistan":[42],"commonly":[44],"mixed":[45],"in":[48,61,122],"daily":[49],"communication.":[50],"Urdu,":[51],"being":[52],"under-resourced":[53],"language,":[54],"have":[55],"no":[56],"substantial":[57],"corpus":[60,76],"hand":[62],"to":[63,81,91,126,149,169],"develop":[64],"speech":[65,75,88],"recognition":[66],"system.":[67],"In":[68],"this":[69],"research,":[70],"readily":[71],"available":[72],"spontaneous":[73],"(25":[77],"hours)":[78],"revised":[80],"use":[82],"it":[83],"enhancement":[85],"read":[87],"LVCSR":[90],"recognize":[92],"data":[96,117,155],"set":[97],"split":[99],"into":[100],"20":[101],"hours":[102,107,112],"train":[104],"5":[106],"test":[109,172],"set.":[110,173],"10":[111],"BroadCast":[115],"(BC)":[116],"are":[118,156],"collected":[119],"annotated":[121],"a":[123],"semi-supervised":[124],"way":[125],"enhance":[127],"further.":[130],"For":[131],"acoustic":[132],"modeling,":[133],"state-of-the-art":[134],"DNN-HMM":[135],"modeling":[136],"technique":[137],"used":[139],"without":[140],"any":[141],"prior":[142],"GMM-HMM":[143],"training":[144],"alignments.":[146],"Various":[147],"techniques":[148],"improve":[150],"model":[152],"using":[153],"monolingual":[154],"investigated.":[157],"The":[158],"overall":[159],"percent":[160],"Word":[161],"Error":[162],"Rate":[163],"(WER)":[164],"reduced":[166],"from":[167],"40.71%":[168],"26.95%":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}