{"id":"https://openalex.org/W4393406202","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482938","title":"A Novel Approach for Bootstrapping and Automatic Transcription of Low Resourced Language Speech Corpus","display_name":"A Novel Approach for Bootstrapping and Automatic Transcription of Low Resourced Language Speech Corpus","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4393406202","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482938"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda60357.2023.10482938","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th 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/A5009926678","display_name":"Mukund K Roy","orcid":"https://orcid.org/0000-0001-6000-0334"},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mukund K Roy","raw_affiliation_strings":["CDAC,SNLP Dept.,Noida,India","SNLP Dept., CDAC, Noida, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CDAC,SNLP Dept.,Noida,India","institution_ids":["https://openalex.org/I1331500379"]},{"raw_affiliation_string":"SNLP Dept., CDAC, Noida, India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101420858","display_name":"Karunesh Arora","orcid":"https://orcid.org/0000-0003-3726-5304"},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Karunesh K Arora","raw_affiliation_strings":["CDAC,SNLP Dept.,Noida,India","SNLP Dept., CDAC, Noida, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CDAC,SNLP Dept.,Noida,India","institution_ids":["https://openalex.org/I1331500379"]},{"raw_affiliation_string":"SNLP Dept., CDAC, Noida, India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074990876","display_name":"Joyanta Basu","orcid":"https://orcid.org/0000-0002-8278-3402"},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Joyanta Basu","raw_affiliation_strings":["CDAC,ASPG Dept.,Kolkata,India","ASPG Dept., CDAC, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CDAC,ASPG Dept.,Kolkata,India","institution_ids":["https://openalex.org/I1331500379"]},{"raw_affiliation_string":"ASPG Dept., CDAC, Kolkata, India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102782582","display_name":"Saikat Basu","orcid":"https://orcid.org/0000-0001-6590-3938"},"institutions":[{"id":"https://openalex.org/I99601430","display_name":"Maulana Abul Kalam Azad University of Technology, West Bengal","ror":"https://ror.org/030tcae29","country_code":"IN","type":"education","lineage":["https://openalex.org/I99601430"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Saikat Basu","raw_affiliation_strings":["MAKAUT,CSE Dept.,Kolkata,India","CSE Dept., MAKAUT, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MAKAUT,CSE Dept.,Kolkata,India","institution_ids":["https://openalex.org/I99601430"]},{"raw_affiliation_string":"CSE Dept., MAKAUT, Kolkata, India","institution_ids":["https://openalex.org/I99601430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074671737","display_name":"Sunita Arora","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunita Arora","raw_affiliation_strings":["CDAC,SNLP Dept.,Noida,India","SNLP Dept., CDAC, Noida, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CDAC,SNLP Dept.,Noida,India","institution_ids":["https://openalex.org/I1331500379"]},{"raw_affiliation_string":"SNLP Dept., CDAC, Noida, India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108625605","display_name":"Shyam S. Agarwal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shyam S Agarwal","raw_affiliation_strings":["KIIT,CSE Dept.,Gurgaon,India","CSE Dept., KIIT, Gurgaon, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KIIT,CSE Dept.,Gurgaon,India","institution_ids":[]},{"raw_affiliation_string":"CSE Dept., KIIT, Gurgaon, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1591,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58041234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.973800003528595,"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":0.973800003528595,"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/bootstrapping","display_name":"Bootstrapping (finance)","score":0.8635073900222778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7888784408569336},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6277098655700684},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5471899509429932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5110069513320923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48520973324775696},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.41995272040367126},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.17377856373786926},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13896140456199646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05134853720664978}],"concepts":[{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.8635073900222778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7888784408569336},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6277098655700684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5471899509429932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5110069513320923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48520973324775696},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.41995272040367126},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.17377856373786926},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13896140456199646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05134853720664978},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda60357.2023.10482938","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th 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":0.7099999785423279,"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":16,"referenced_works":["https://openalex.org/W1983190981","https://openalex.org/W1988099331","https://openalex.org/W2049155070","https://openalex.org/W2055487029","https://openalex.org/W2075201173","https://openalex.org/W2091746061","https://openalex.org/W2938732626","https://openalex.org/W3010812523","https://openalex.org/W3015356564","https://openalex.org/W3036601975","https://openalex.org/W3153199526","https://openalex.org/W3213618310","https://openalex.org/W4224322103","https://openalex.org/W4287075881","https://openalex.org/W4298382487","https://openalex.org/W6779089044"],"related_works":["https://openalex.org/W2028097510","https://openalex.org/W2505877856","https://openalex.org/W113515668","https://openalex.org/W2155576284","https://openalex.org/W2068512280","https://openalex.org/W1587721369","https://openalex.org/W2550534525","https://openalex.org/W4214593397","https://openalex.org/W1833998246","https://openalex.org/W175497273"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"systems":[4],"have":[5],"made":[6],"significant":[7],"advancements":[8],"in":[9,155],"the":[10,18,28,47,83,86,106,113,157],"context":[11],"of":[12,21,30,49,51,130,135],"high-resource":[13],"languages,":[14],"primarily":[15],"attributable":[16],"to":[17,40,71,104,144],"abundant":[19],"availability":[20],"extensive":[22],"and":[23,78,109,138,151],"diverse":[24],"speech":[25,73,99],"datasets.":[26],"Nevertheless,":[27],"dearth":[29],"annotated":[31],"data":[32,139],"remains":[33],"a":[34,126],"substantial":[35],"hurdle":[36],"when":[37],"it":[38],"comes":[39],"low-resource":[41,56],"languages.":[42,64],"This":[43,96],"study":[44],"delves":[45],"into":[46],"feasibility":[48],"development":[50],"an":[52],"ASR":[53,114],"system":[54],"for":[55,124],"languages":[57,148],"by":[58],"leveraging":[59],"pre-trained":[60],"models":[61],"from":[62,75],"other":[63,145],"The":[65,116,132],"fine-tuned":[66],"model":[67],"is":[68,89,101],"then":[69],"deployed":[70],"transcribe":[72],"segments":[74],"news":[76,94],"bulletins":[77],"audio":[79],"content":[80],"found":[81],"on":[82],"web.":[84],"Subsequently,":[85],"generated":[87],"transcript":[88],"heuristically":[90],"aligned":[91,98],"with":[92],"existing":[93,107],"script.":[95],"newly":[97],"corpus":[100],"used":[102],"incrementally":[103],"augment":[105],"corpus,":[108],"thus":[110,152],"progressively":[111],"bootstrapping":[112],"models.":[115],"proposed":[117,133],"work":[118],"has":[119],"been":[120],"effectively":[121],"carried":[122],"out":[123],"Dogri,":[125],"low":[127,146],"resource":[128,147,158],"language":[129],"India.":[131],"approach":[134],"incremental":[136],"learning":[137],"augmentation":[140],"can":[141],"be":[142],"applied":[143],"as":[149],"well,":[150],"would":[153],"help":[154],"bridging":[156],"gap.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2025-10-10T00:00:00"}