{"id":"https://openalex.org/W4393406218","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482936","title":"Leveraging Cross Lingual Speech Representations To Build ASR For Under-resourced Languages","display_name":"Leveraging Cross Lingual Speech Representations To Build ASR For Under-resourced Languages","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4393406218","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482936"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda60357.2023.10482936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda60357.2023.10482936","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":"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/A5021721976","display_name":"Sougata Mukherjee","orcid":"https://orcid.org/0000-0001-5671-8714"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sougata Mukherjee","raw_affiliation_strings":["Indian Institute of Technology Dharwad,Dept. of Electrical, Electronics and Communication Engineering,Dharwad,India","Dept. of Electrical, Electronics and Communication Engineering, Indian Institute of Technology Dharwad, Dharwad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Dharwad,Dept. of Electrical, Electronics and Communication Engineering,Dharwad,India","institution_ids":["https://openalex.org/I4210152718"]},{"raw_affiliation_string":"Dept. of Electrical, Electronics and Communication Engineering, Indian Institute of Technology Dharwad, Dharwad, India","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093311695","display_name":"Prashant Bannulmath","orcid":"https://orcid.org/0009-0001-0942-7823"},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]},{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]},{"id":"https://openalex.org/I4387153068","display_name":"Indian Institute of Information Technology Dharwad","ror":"https://ror.org/0237jt454","country_code":null,"type":"education","lineage":["https://openalex.org/I4387153068"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prashant Bannulmath","raw_affiliation_strings":["Indian Institute of Information Technology,Dept. of Electronics and Communication Engineering,Dharwad,India","Dept. of Electronics and Communication Engineering, Indian Institute of Information Technology, Dharwad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology,Dept. of Electronics and Communication Engineering,Dharwad,India","institution_ids":["https://openalex.org/I26072440","https://openalex.org/I4210152718"]},{"raw_affiliation_string":"Dept. of Electronics and Communication Engineering, Indian Institute of Information Technology, Dharwad, India","institution_ids":["https://openalex.org/I26072440","https://openalex.org/I4210152718","https://openalex.org/I4387153068"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108978346","display_name":"K T Deepak","orcid":null},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]},{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]},{"id":"https://openalex.org/I4387153068","display_name":"Indian Institute of Information Technology Dharwad","ror":"https://ror.org/0237jt454","country_code":null,"type":"education","lineage":["https://openalex.org/I4387153068"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Deepak K T","raw_affiliation_strings":["Indian Institute of Information Technology,Dept. of Electronics and Communication Engineering,Dharwad,India","Dept. of Electronics and Communication Engineering, Indian Institute of Information Technology, Dharwad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology,Dept. of Electronics and Communication Engineering,Dharwad,India","institution_ids":["https://openalex.org/I26072440","https://openalex.org/I4210152718"]},{"raw_affiliation_string":"Dept. of Electronics and Communication Engineering, Indian Institute of Information Technology, Dharwad, India","institution_ids":["https://openalex.org/I26072440","https://openalex.org/I4210152718","https://openalex.org/I4387153068"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052129812","display_name":"S. R. Mahadeva Prasanna","orcid":"https://orcid.org/0000-0002-8135-7938"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. R. Mahadeva Prasanna","raw_affiliation_strings":["Indian Institute of Technology,Dept. of Electrical, Electronics and Communication Engineering,Dharwad,India","Dept. of Electrical, Electronics and Communication Engineering, Indian Institute of Technology, Dharwad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Dept. of Electrical, Electronics and Communication Engineering,Dharwad,India","institution_ids":["https://openalex.org/I4210152718"]},{"raw_affiliation_string":"Dept. of Electrical, Electronics and Communication Engineering, Indian Institute of Technology, Dharwad, India","institution_ids":["https://openalex.org/I4210152718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52557461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9934999942779541,"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":0.9934999942779541,"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/T12031","display_name":"Speech and dialogue systems","score":0.9878000020980835,"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":0.9240999817848206,"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/computer-science","display_name":"Computer science","score":0.8082733154296875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5425302982330322},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.502593994140625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37517961859703064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082733154296875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5425302982330322},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.502593994140625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37517961859703064}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda60357.2023.10482936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda60357.2023.10482936","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W108866686","https://openalex.org/W628926157","https://openalex.org/W1494198834","https://openalex.org/W2003333103","https://openalex.org/W2072223048","https://openalex.org/W2589568283","https://openalex.org/W2973049979","https://openalex.org/W2981991061","https://openalex.org/W3113594615","https://openalex.org/W4224322103","https://openalex.org/W4247827174","https://openalex.org/W4287075881","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6620143334","https://openalex.org/W6733694492","https://openalex.org/W6769238691","https://openalex.org/W6787141514","https://openalex.org/W6798423582","https://openalex.org/W6810631401","https://openalex.org/W6810673746","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Automatic":[0,22],"speech":[1,45],"recognition":[2],"(ASR)":[3],"technology":[4],"can":[5],"help":[6],"document":[7],"and":[8,44,53,55,78,114,123,145,173,175,180,190,203,211,243],"preserve":[9],"under-resourced":[10,96],"tribal":[11,27,49,228],"languages":[12,28,50,148,229],"by":[13],"converting":[14],"spoken":[15],"words":[16],"into":[17],"text.":[18],"But":[19],"building":[20,41],"robust":[21],"Speech":[23],"Recognition(ASR)":[24],"models":[25],"for":[26,47,62,95,158,163,185,209],"is":[29,65],"challenging":[30],"due":[31],"to":[32,57,67,87,152],"scarcity":[33],"of":[34,42,82,91,143,161,171,178,188,201,207,221,240],"annotated":[35,93],"data.":[36,84],"This":[37],"work":[38,216],"shows":[39],"the":[40,80,89,118,131,154,159,219,225],"text":[43],"corpora":[46],"two":[48,227],"namely":[51],"Lambani":[52,124,189,210],"Kui":[54,122,191],"attempts":[56],"develop":[58],"an":[59],"ASR":[60,162],"system":[61],"those.":[63],"Wav2vec2.0":[64],"known":[66],"learn":[68],"higher":[69],"dimensional":[70],"powerful":[71],"representation":[72],"directly":[73],"from":[74],"raw":[75],"audio":[76],"data":[77,94,105,119,144,194,241],"boost":[79],"performance":[81,220],"under-resource":[83],"In":[85],"order":[86],"overcome":[88],"limitation":[90],"scarce":[92],"languages,":[97,128],"wav2vec2.0":[98,132,167],"framework":[99,133,168],"has":[100,137,149,182,231],"been":[101,138,150,183,233],"used":[102,151,234],"along":[103],"with":[104,224,237],"augmentation":[106,195],"techniques":[107,196],"like":[108],"Gaussian":[109],"noise":[110],"addition,":[111],"Pitch":[112],"variation":[113],"Reverberation":[115],"which":[116,136,230],"increases":[117],"synthetically.":[120],"As":[121],"are":[125],"both":[126],"indic":[127,147],"so":[129],"in":[130,205],"a":[134,169,176,198],"model":[135],"pretrained":[139],"on":[140],"10k":[141],"hours":[142,187],"23":[146],"leverage":[153],"cross":[155],"lingual":[156],"representations":[157],"development":[160],"these":[164],"languages.":[165],"Using":[166],"WER":[170,208],"41.55%":[172],"49.57%":[174],"CER":[177],"12.49%":[179],"12.52%":[181],"achieved":[184],"5":[186],"respectively.":[192],"The":[193],"gives":[197],"relative":[199],"improvement":[200],"8.64%":[202],"3.73%":[204],"terms":[206],"Kui.":[212],"Besides":[213],"this,":[214],"this":[215],"also":[217],"compares":[218],"English":[222],"language":[223],"other":[226],"already":[232],"during":[235],"pre-training":[236],"same":[238],"amount":[239],"setting":[242],"framework.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}