{"id":"https://openalex.org/W4405633916","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800277","title":"Enhancing Phoneme Recognition in the Bengali Language Through Fine-Tuning of Multilingual Model","display_name":"Enhancing Phoneme Recognition in the Bengali Language Through Fine-Tuning of Multilingual Model","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405633916","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800277"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th 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":"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/A5064272669","display_name":"Akash Deep","orcid":"https://orcid.org/0000-0001-8678-2303"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Akash Deep","raw_affiliation_strings":["Indian Institute of Technology,Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044762857","display_name":"Puja Bharati","orcid":"https://orcid.org/0009-0000-3468-623X"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Puja Bharati","raw_affiliation_strings":["Indian Institute of Technology,Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083665711","display_name":"Sabyasachi Chandra","orcid":"https://orcid.org/0009-0003-3051-247X"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sabyasachi Chandra","raw_affiliation_strings":["Indian Institute of Technology,Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026317147","display_name":"Debolina Pramanik","orcid":"https://orcid.org/0009-0004-2170-4450"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Debolina Pramanik","raw_affiliation_strings":["Indian Institute of Technology,Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Korra Siva Naik","orcid":null},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Korra Siva Naik","raw_affiliation_strings":["Indian Institute of Technology,Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101233946","display_name":"Shayamal Kumar Das Mandal","orcid":null},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shayamal Kumar Das Mandal","raw_affiliation_strings":["Indian Institute of Technology,Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26084669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9812999963760376,"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":0.9812999963760376,"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":0.9681000113487244,"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/bengali","display_name":"Bengali","score":0.9510688185691833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.763485312461853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5914716124534607},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5488723516464233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5115038156509399},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5062312483787537}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.9510688185691833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.763485312461853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5914716124534607},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5488723516464233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115038156509399},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5062312483787537}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th 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":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2195354","https://openalex.org/W108866686","https://openalex.org/W1526236009","https://openalex.org/W2130414229","https://openalex.org/W2140777099","https://openalex.org/W2166637769","https://openalex.org/W2889074736","https://openalex.org/W2963242190","https://openalex.org/W3015877095","https://openalex.org/W3094359917","https://openalex.org/W3203953122","https://openalex.org/W4200300291","https://openalex.org/W4322714819","https://openalex.org/W4388400684","https://openalex.org/W4392903557","https://openalex.org/W6631362777","https://openalex.org/W6691509046","https://openalex.org/W6779069753","https://openalex.org/W6779469704","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2084490135","https://openalex.org/W4298170800","https://openalex.org/W2895890526","https://openalex.org/W617692174","https://openalex.org/W2794758919","https://openalex.org/W4232781930","https://openalex.org/W2028401451","https://openalex.org/W2769530083","https://openalex.org/W3161006337","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Phoneme":[0,90,212],"recognition":[1,6,91,202],"is":[2,29,169],"essential":[3],"in":[4,32,199],"speech":[5],"systems,":[7],"allowing":[8],"for":[9,130],"precise":[10],"transcription":[11,26],"of":[12,82,92,165,177,203,216],"spoken":[13,50],"language":[14,33,51,167,205],"into":[15],"text.":[16],"This":[17],"technology":[18],"underpins":[19],"virtual":[20],"assistants,":[21],"voice":[22],"search,":[23],"and":[24,42],"automated":[25],"services.":[27],"It":[28],"also":[30],"vital":[31],"learning":[34],"applications,":[35],"where":[36],"it":[37,129],"helps":[38],"with":[39,115],"pronunciation":[40],"training":[41],"accent":[43],"reduction":[44],"by":[45,127,221],"offering":[46],"real-time":[47],"feedback":[48],"on":[49],"accuracy.":[52],"Phonemes":[53],"are":[54,75,79,121,193],"the":[55,70,80,108,123,131,178,200,211,225],"distinct":[56],"sounds":[57,72],"that":[58,84,206],"create":[59],"meaningful":[60],"contrasts":[61],"within":[62],"a":[63,87,143,155],"specific":[64],"language,":[65],"while":[66],"phones":[67,83],"refer":[68],"to":[69,86,106,152,180,183,196,224],"actual":[71],"produced,":[73],"which":[74,168],"generally":[76],"language-independent.":[77],"Allophones":[78],"set":[81],"correspond":[85],"particular":[88,156],"phoneme.":[89,157],"low":[93],"resource":[94],"languages":[95],"using":[96,148],"Automatic":[97],"Speech":[98],"Recognition":[99],"(ASR)":[100],"model":[101,114,126,137,182,226],"produce":[102],"suboptimal":[103],"results,":[104],"hence":[105],"improve":[107],"result,":[109],"we":[110,120,160,173,192,207],"can":[111,208],"use":[112],"pre-trained":[113,125,136],"fine-tuning.":[116,228],"In":[117],"this":[118],"work,":[119],"utilizing":[122],"multilingual":[124,135],"fine-tuning":[128],"Bengali":[132,166,204],"language.":[133],"A":[134],"called":[138],"Allosaurus":[139],"makes":[140],"predictions":[141],"over":[142],"common":[144],"phone":[145],"inventory":[146],"before":[147],"an":[149],"allophone":[150],"layer":[151],"map":[153],"onto":[154],"For":[158],"fine-tuning,":[159],"require":[161],"phoneme":[162,181,185,201],"transcribed":[163,186],"dataset":[164],"not":[170],"available.":[171],"Here":[172],"have":[174],"used":[175],"one":[176],"text":[179],"get":[184],"data.":[187],"Through":[188],"our":[189,217],"proposed":[190],"approach,":[191],"able":[194],"achieve":[195],"significant":[197],"improvements":[198],"see":[209],"as":[210],"Error":[213],"Rate":[214],"(PER)":[215],"test":[218],"file":[219],"reduces":[220],"95.65%":[222],"compared":[223],"without":[227]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}