{"id":"https://openalex.org/W4205868073","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660552","title":"A Multi-Genre Urdu Broadcast Speech Recognition System","display_name":"A Multi-Genre Urdu Broadcast Speech Recognition System","publication_year":2021,"publication_date":"2021-11-18","ids":{"openalex":"https://openalex.org/W4205868073","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660552"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda202152914.2021.9660552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th 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/A5051790350","display_name":"Erbaz Khan","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":"Erbaz Khan","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":"middle","author":{"id":"https://openalex.org/A5034131804","display_name":"Farah Adeeba","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farah Adeeba","raw_affiliation_strings":["Department of Computer Science, New Campus, KSK., University of Engineering and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, New Campus, KSK., University of Engineering and Technology","institution_ids":[]}]},{"author_position":"last","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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5597,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74622091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"30"},"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":0.9988999962806702,"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":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.8466251492500305},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7851777076721191},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.767663836479187},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7187991142272949},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6323098540306091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.601025402545929},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5386173129081726},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4961453378200531},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49342599511146545},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.4745650589466095},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4631819725036621},{"id":"https://openalex.org/keywords/urdu","display_name":"Urdu","score":0.46090778708457947},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46038153767585754},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.45229920744895935},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44521647691726685},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.41964447498321533},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2834700345993042},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.23444464802742004},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07833582162857056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8466251492500305},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7851777076721191},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.767663836479187},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7187991142272949},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6323098540306091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.601025402545929},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5386173129081726},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4961453378200531},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49342599511146545},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.4745650589466095},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4631819725036621},{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.46090778708457947},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46038153767585754},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.45229920744895935},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44521647691726685},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.41964447498321533},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2834700345993042},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.23444464802742004},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07833582162857056},{"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/o-cocosda202152914.2021.9660552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th 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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W100598793","https://openalex.org/W182831726","https://openalex.org/W1631260214","https://openalex.org/W2117671523","https://openalex.org/W2125838338","https://openalex.org/W2294256115","https://openalex.org/W2311274668","https://openalex.org/W2407731605","https://openalex.org/W2787420813","https://openalex.org/W2803306015","https://openalex.org/W2972354933","https://openalex.org/W2983036158","https://openalex.org/W3117353267","https://openalex.org/W6636811518","https://openalex.org/W6678615056","https://openalex.org/W6698102006","https://openalex.org/W6751169377"],"related_works":["https://openalex.org/W2159992105","https://openalex.org/W2130596402","https://openalex.org/W2124470186","https://openalex.org/W151018310","https://openalex.org/W3081187864","https://openalex.org/W3105992103","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W2784059283","https://openalex.org/W2291624303"],"abstract_inverted_index":{"This":[0],"paper":[1],"reports":[2],"the":[3,55,92,118,124],"development":[4],"of":[5,24,73,85,136],"a":[6,13,70,108,133],"multi-genre":[7,88],"Urdu":[8],"Broadcast":[9],"(BC)":[10],"corpus":[11,23,72],"and":[12,32,52,60,91,123,142],"Large":[14],"Vocabulary":[15],"Continuous":[16],"Speech":[17,126],"Recognition":[18,127],"(LVCSR)":[19],"system.":[20],"BC":[21,87],"speech":[22,89],"98":[25],"hours":[26,84],"from":[27],"453":[28],"speakers":[29],"is":[30,41,99,113],"collected":[31],"annotated.":[33],"For":[34,54],"acoustic":[35],"modeling,":[36],"Time-delay":[37],"Neural":[38,62],"Network":[39,63],"(TDNN)":[40],"developed":[42,68,78],"with":[43],"prior":[44],"Gaussian":[45],"Mixture":[46],"Model-Hidden":[47],"Markov":[48],"Model":[49,105],"(GMM-HMM)":[50],"training":[51],"alignments.":[53],"language":[56],"model,":[57],"3-gram,":[58],"4-gram":[59],"Recurrent":[61],"(RNN)":[64],"based":[65,103],"models":[66,79],"are":[67,80],"on":[69,82],"text":[71],"188":[74],"million":[75],"words.":[76],"The":[77,130],"tested":[81],"4.3":[83],"unseen":[86],"dataset":[90],"best":[93],"Word":[94],"Error":[95],"Rate":[96],"(WER)":[97],"18.59%":[98],"achieved":[100],"using":[101],"RNN":[102],"Language":[104],"(LM).":[106],"Moreover,":[107],"detailed":[109],"word":[110,137],"error":[111],"analysis":[112],"carried":[114],"out":[115],"to":[116],"compare":[117],"errors":[119],"made":[120],"by":[121,139],"humans":[122,141],"Automatic":[125],"(ASR)":[128],"System.":[129],"results":[131],"showed":[132],"similar":[134],"behavior":[135],"misrecognitions":[138],"both":[140],"ASR.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}