{"id":"https://openalex.org/W4285351314","doi":"https://doi.org/10.1109/icccs51487.2021.9776324","title":"An end-to-end interpolated Automatic speech recognition system with punctuated transcripts for the Hindi language","display_name":"An end-to-end interpolated Automatic speech recognition system with punctuated transcripts for the Hindi language","publication_year":2021,"publication_date":"2021-10-04","ids":{"openalex":"https://openalex.org/W4285351314","doi":"https://doi.org/10.1109/icccs51487.2021.9776324"},"language":"en","primary_location":{"id":"doi:10.1109/icccs51487.2021.9776324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccs51487.2021.9776324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 6th International Conference on Computing, Communication and Security (ICCCS)","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/A5068278005","display_name":"Saurav Joshi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saurav Joshi","raw_affiliation_strings":["Machine Learning Engineer, Convin.ai India Research Group,Dehradun,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Engineer, Convin.ai India Research Group,Dehradun,India","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Vishal Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vishal Kumar","raw_affiliation_strings":["Bipin Tripathi Kumaon Institute of Technology,Dept. of Computer Science & Eng.,Dwarahat,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bipin Tripathi Kumaon Institute of Technology,Dept. of Computer Science & Eng.,Dwarahat,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24489062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"1","last_page":"7"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/punctuation","display_name":"Punctuation","score":0.8669167757034302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8387386202812195},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.6968480944633484},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6168111562728882},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5650404691696167},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5340408682823181},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.519832193851471},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5191954374313354},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5018525123596191},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.45043444633483887},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31707510352134705},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1284375786781311},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07378268241882324}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.8669167757034302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8387386202812195},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.6968480944633484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6168111562728882},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5650404691696167},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5340408682823181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.519832193851471},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5191954374313354},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5018525123596191},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.45043444633483887},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31707510352134705},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1284375786781311},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07378268241882324},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccs51487.2021.9776324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccs51487.2021.9776324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 6th International Conference on Computing, Communication and Security (ICCCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W16967297","https://openalex.org/W32283220","https://openalex.org/W38163879","https://openalex.org/W126222424","https://openalex.org/W1491238342","https://openalex.org/W1502984613","https://openalex.org/W1524333225","https://openalex.org/W1587490638","https://openalex.org/W1815076433","https://openalex.org/W1975570633","https://openalex.org/W1984541135","https://openalex.org/W2132991150","https://openalex.org/W2133564696","https://openalex.org/W2146502635","https://openalex.org/W2160815625","https://openalex.org/W2166116787","https://openalex.org/W2402146185","https://openalex.org/W2403334028","https://openalex.org/W2789982723","https://openalex.org/W2885195348","https://openalex.org/W2938722449","https://openalex.org/W2991356003","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2936002343","https://openalex.org/W2370831213","https://openalex.org/W2188883480","https://openalex.org/W4315704968","https://openalex.org/W1592364192","https://openalex.org/W4285478380","https://openalex.org/W656840002"],"abstract_inverted_index":{"The":[0,23],"Automatic":[1],"Speech":[2],"Recognition":[3],"System":[4],"(ASR)":[5],"produces":[6],"transcripts":[7],"that":[8],"often":[9],"are":[10],"misinterpreted":[11],"and":[12,21,32,61,79,90,117],"confuses":[13],"the":[14,28,52,57,66,73,100,108,112,118],"reader":[15],"due":[16],"to":[17,71,75,94],"lack":[18],"of":[19,25,41],"context":[20],"punctuations.":[22],"presence":[24],"punctuation":[26,119],"in":[27,34,56,65],"text":[29],"improves":[30],"readability":[31],"helps":[33],"better":[35],"cognitive":[36],"understanding.":[37],"A":[38],"wide":[39],"variety":[40],"work":[42],"has":[43],"been":[44],"done":[45,122],"on":[46],"English":[47,60],"but":[48],"Hindi":[49,101],"which":[50],"is":[51,105,121],"third-largest":[53],"spoken":[54],"language":[55,92],"world,":[58],"after":[59],"Mandarin,":[62],"still":[63],"remains":[64],"shadows.":[67],"This":[68],"paper":[69],"aims":[70],"extend":[72],"technology":[74],"a":[76],"wider":[77],"section":[78],"introduces":[80],"an":[81,85,127],"end-to-end":[82],"system,":[83],"interpolating":[84],"automatic":[86],"speech":[87],"recognition":[88],"system":[89],"natural":[91],"processing":[93],"produce":[95],"high-quality":[96],"punctuated":[97],"transcriptions":[98],"for":[99],"language.":[102],"An":[103],"ASR":[104],"implemented":[106],"using":[107],"Kaldi":[109],"toolkit":[110],"leveraging":[111],"hybrid":[113],"deep":[114],"neural":[115],"networks":[116],"restoration":[120],"with":[123,126],"Bidirectional":[124],"RNNs":[125],"attention":[128],"network.":[129]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}