{"id":"https:\/\/openalex.org\/W7127053091","doi":"https:\/\/doi.org\/10.1007\/978-3-032-16632-6_16","title":"KUI-2SR: A Unified Speech and Speaker Recognizer for KUI Language","display_name":"KUI-2SR: A Unified Speech and Speaker Recognizer for KUI Language","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https:\/\/openalex.org\/W7127053091","doi":"https:\/\/doi.org\/10.1007\/978-3-032-16632-6_16"},"language":"en","primary_location":{"id":"doi:10.1007\/978-3-032-16632-6_16","is_oa":true,"landing_page_url":"https:\/\/doi.org\/10.1007\/978-3-032-16632-6_16","pdf_url":null,"source":{"id":"https:\/\/openalex.org\/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https:\/\/openalex.org\/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https:\/\/openalex.org\/P4310319900","https:\/\/openalex.org\/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https:\/\/openalex.org\/licenses\/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https:\/\/doi.org\/10.1007\/978-3-032-16632-6_16","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https:\/\/openalex.org\/A5106203596","display_name":"Malay Kumar Majhi","orcid":null},"institutions":[{"id":"https:\/\/openalex.org\/I155837530","display_name":"National Institute of Technology Durgapur","ror":"https:\/\/ror.org\/04ds0jm32","country_code":"IN","type":"education","lineage":["https:\/\/openalex.org\/I155837530"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Malay Kumar Majhi","raw_affiliation_strings":["National Institute of Technology Durgapur, Durgapur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Durgapur, Durgapur, India","institution_ids":["https:\/\/openalex.org\/I155837530"]}]},{"author_position":"last","author":{"id":"https:\/\/openalex.org\/A5124744014","display_name":"Sujan Kumar Saha","orcid":null},"institutions":[{"id":"https:\/\/openalex.org\/I155837530","display_name":"National Institute of Technology Durgapur","ror":"https:\/\/ror.org\/04ds0jm32","country_code":"IN","type":"education","lineage":["https:\/\/openalex.org\/I155837530"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sujan Kumar Saha","raw_affiliation_strings":["National Institute of Technology Durgapur, Durgapur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Durgapur, Durgapur, India","institution_ids":["https:\/\/openalex.org\/I155837530"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https:\/\/openalex.org\/A5106203596","https:\/\/openalex.org\/A5124744014"],"corresponding_institution_ids":["https:\/\/openalex.org\/I155837530"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10578478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https:\/\/openalex.org\/T10201","display_name":"Speech Recognition and Synthesis","score":0.20080000162124634,"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":0.20080000162124634,"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\/T13029","display_name":"South Asian Studies and Conflicts","score":0.08169999718666077,"subfield":{"id":"https:\/\/openalex.org\/subfields\/3320","display_name":"Political Science and International Relations"},"field":{"id":"https:\/\/openalex.org\/fields\/33","display_name":"Social Sciences"},"domain":{"id":"https:\/\/openalex.org\/domains\/2","display_name":"Social Sciences"}},{"id":"https:\/\/openalex.org\/T13194","display_name":"ICT in Developing Communities","score":0.07810000330209732,"subfield":{"id":"https:\/\/openalex.org\/subfields\/1710","display_name":"Information Systems"},"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\/word-error-rate","display_name":"Word error rate","score":0.7138000130653381},{"id":"https:\/\/openalex.org\/keywords\/speaker-recognition","display_name":"Speaker recognition","score":0.5698000192642212},{"id":"https:\/\/openalex.org\/keywords\/transfer-of-learning","display_name":"Transfer of learning","score":0.45980000495910645},{"id":"https:\/\/openalex.org\/keywords\/character","display_name":"Character (mathematics)","score":0.4496999979019165},{"id":"https:\/\/openalex.org\/keywords\/identification","display_name":"Identification (biology)","score":0.4352000057697296},{"id":"https:\/\/openalex.org\/keywords\/transfer","display_name":"Transfer (computing)","score":0.40869998931884766},{"id":"https:\/\/openalex.org\/keywords\/spoken-language","display_name":"Spoken language","score":0.4041000008583069},{"id":"https:\/\/openalex.org\/keywords\/language-model","display_name":"Language model","score":0.3650999963283539}],"concepts":[{"id":"https:\/\/openalex.org\/C41008148","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q21198","display_name":"Computer science","level":0,"score":0.9146000146865845},{"id":"https:\/\/openalex.org\/C40969351","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q3516228","display_name":"Word error rate","level":2,"score":0.7138000130653381},{"id":"https:\/\/openalex.org\/C28490314","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q189436","display_name":"Speech recognition","level":1,"score":0.6664999723434448},{"id":"https:\/\/openalex.org\/C133892786","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5698000192642212},{"id":"https:\/\/openalex.org\/C204321447","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q30642","display_name":"Natural language processing","level":1,"score":0.5400000214576721},{"id":"https:\/\/openalex.org\/C154945302","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5264999866485596},{"id":"https:\/\/openalex.org\/C150899416","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1820378","display_name":"Transfer of learning","level":2,"score":0.45980000495910645},{"id":"https:\/\/openalex.org\/C2780861071","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4496999979019165},{"id":"https:\/\/openalex.org\/C116834253","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4352000057697296},{"id":"https:\/\/openalex.org\/C2776175482","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.40869998931884766},{"id":"https:\/\/openalex.org\/C2776230583","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1322198","display_name":"Spoken language","level":2,"score":0.4041000008583069},{"id":"https:\/\/openalex.org\/C137293760","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q3621696","display_name":"Language model","level":2,"score":0.3650999963283539},{"id":"https:\/\/openalex.org\/C90805587","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q10944557","display_name":"Word (group theory)","level":2,"score":0.350600004196167},{"id":"https:\/\/openalex.org\/C12725497","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3497999906539917},{"id":"https:\/\/openalex.org\/C2986627078","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1145189","display_name":"Speaker identification","level":3,"score":0.3222000002861023},{"id":"https:\/\/openalex.org\/C91863865","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q4349497","display_name":"Speech corpus","level":3,"score":0.32089999318122864},{"id":"https:\/\/openalex.org\/C3018824978","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q2894891","display_name":"Error analysis","level":2,"score":0.3190000057220459},{"id":"https:\/\/openalex.org\/C2776401178","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2996000051498413},{"id":"https:\/\/openalex.org\/C149838564","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.2915000021457672},{"id":"https:\/\/openalex.org\/C61328038","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q3358061","display_name":"Speech processing","level":2,"score":0.289000004529953},{"id":"https:\/\/openalex.org\/C155635449","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q4674699","display_name":"Acoustic model","level":3,"score":0.26899999380111694},{"id":"https:\/\/openalex.org\/C129792486","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1050419","display_name":"Language identification","level":3,"score":0.26409998536109924},{"id":"https:\/\/openalex.org\/C204201278","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2615000009536743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007\/978-3-032-16632-6_16","is_oa":true,"landing_page_url":"https:\/\/doi.org\/10.1007\/978-3-032-16632-6_16","pdf_url":null,"source":{"id":"https:\/\/openalex.org\/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https:\/\/openalex.org\/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https:\/\/openalex.org\/P4310319900","https:\/\/openalex.org\/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https:\/\/openalex.org\/licenses\/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007\/978-3-032-16632-6_16","is_oa":true,"landing_page_url":"https:\/\/doi.org\/10.1007\/978-3-032-16632-6_16","pdf_url":null,"source":{"id":"https:\/\/openalex.org\/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https:\/\/openalex.org\/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https:\/\/openalex.org\/P4310319900","https:\/\/openalex.org\/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https:\/\/openalex.org\/licenses\/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https:\/\/metadata.un.org\/sdg\/4","display_name":"Quality Education","score":0.7058086395263672}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https:\/\/openalex.org\/W1813696425","https:\/\/openalex.org\/W2034725917","https:\/\/openalex.org\/W2055487029","https:\/\/openalex.org\/W2080213370","https:\/\/openalex.org\/W2127643134","https:\/\/openalex.org\/W2128454066","https:\/\/openalex.org\/W2580621357","https:\/\/openalex.org\/W2767071179","https:\/\/openalex.org\/W2783208898","https:\/\/openalex.org\/W2808631503","https:\/\/openalex.org\/W2895103375","https:\/\/openalex.org\/W2906459023","https:\/\/openalex.org\/W2963027641","https:\/\/openalex.org\/W2972369255","https:\/\/openalex.org\/W3095184753","https:\/\/openalex.org\/W3147984406","https:\/\/openalex.org\/W3153199526","https:\/\/openalex.org\/W3198214208","https:\/\/openalex.org\/W4327814179","https:\/\/openalex.org\/W4372270069","https:\/\/openalex.org\/W4401049845","https:\/\/openalex.org\/W4409124122"],"related_works":[],"abstract_inverted_index":{"This":[0,159],"study":[1],"presents":[2],"the":[3,12,20,110,113,131,151,162],"first":[4],"unified":[5],"speech":[6,55,97],"and":[7,32,89,120,145,169],"speaker":[8,106,152,157,170],"recognition":[9,56,81,171],"system":[10,62,114],"for":[11,44],"Kui":[13,15,96],"language.":[14],"is":[16,27,42,72],"predominantly":[17],"spoken":[18,118],"in":[19,58,176],"western":[21],"region":[22],"of":[23,164],"Odisha,":[24],"India.":[25],"It":[26],"primarily":[28],"an":[29,93],"oral":[30],"language":[31],"does":[33],"not":[34,49],"have":[35],"its":[36],"own":[37],"script.":[38],"The":[39,126],"Odia":[40],"script":[41],"used":[43],"written":[45],"communication.":[46],"We":[47],"did":[48],"find":[50],"any":[51],"open":[52],"resources":[53],"or":[54],"systems":[57],"Kui.":[59,181],"Our":[60],"proposed":[61],"follows":[63],"a":[64,68,75,105],"Bi-modular":[65],"pipeline:":[66],"first,":[67],"baseline":[69],"ASR":[70,174],"model":[71],"established":[73],"using":[74,92,99],"Transformer-based":[76],"encoder.":[77],"To":[78],"further":[79],"improve":[80],"accuracy,":[82],"we":[83,103],"employ":[84],"two":[85],"multilingual":[86,133,166],"pre-trained":[87,134],"models":[88],"fine-tune":[90],"them":[91],"in-house":[94],"continuous":[95],"dataset":[98],"transfer":[100,135,167],"learning.":[101],"Next,":[102],"integrate":[104],"identification":[107,153],"module":[108,154],"within":[109],"framework,":[111],"enabling":[112],"to":[115,123,172],"simultaneously":[116],"recognize":[117],"content":[119],"attribute":[121],"it":[122],"individual":[124],"speakers.":[125],"experimental":[127],"results":[128],"demonstrate":[129],"that":[130],"large":[132],"learning":[136,168],"approach":[137],"significantly":[138],"reduces":[139],"both":[140],"Word":[141],"Error":[142,147],"Rate":[143,148],"(WER)":[144],"Character":[146],"(CER),":[149],"while":[150],"provides":[155],"robust":[156],"recognition.":[158],"work":[160],"highlights":[161],"potential":[163],"combining":[165],"advance":[173],"research":[175],"low-resource":[177],"languages":[178],"such":[179],"as":[180]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-02-03T00:00:00"}