{"id":"https://openalex.org/W4410342011","doi":"https://doi.org/10.1109/ncc63735.2025.10983901","title":"A Deep Learning-Based Study on Inter-Language Confusion Assessment Using Spoken Language Identification for Indian Languages","display_name":"A Deep Learning-Based Study on Inter-Language Confusion Assessment Using Spoken Language Identification for Indian Languages","publication_year":2025,"publication_date":"2025-03-06","ids":{"openalex":"https://openalex.org/W4410342011","doi":"https://doi.org/10.1109/ncc63735.2025.10983901"},"language":"en","primary_location":{"id":"doi:10.1109/ncc63735.2025.10983901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc63735.2025.10983901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 National Conference on Communications (NCC)","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":null,"display_name":"Bhagyamuni Rajak","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":true,"raw_author_name":"Bhagyamuni Rajak","raw_affiliation_strings":["IIT Kharagpur,Dept. of Electronics & Electrical Communication Engineering,West Bengal,India"],"affiliations":[{"raw_affiliation_string":"IIT Kharagpur,Dept. of Electronics & Electrical Communication Engineering,West Bengal,India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113074555","display_name":"Souvik Sinha","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":"Souvik Sinha","raw_affiliation_strings":["IIT Kharagpur,Dept. of Electronics & Electrical Communication Engineering,West Bengal,India"],"affiliations":[{"raw_affiliation_string":"IIT Kharagpur,Dept. of Electronics & Electrical Communication Engineering,West Bengal,India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025812658","display_name":"Spandan Dey","orcid":"https://orcid.org/0000-0003-1770-754X"},"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":"Spandan Dey","raw_affiliation_strings":["IIT Kharagpur,Dept. of Electronics & Electrical Communication Engineering,West Bengal,India"],"affiliations":[{"raw_affiliation_string":"IIT Kharagpur,Dept. of Electronics & Electrical Communication Engineering,West Bengal,India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069790572","display_name":"Goutam Saha","orcid":"https://orcid.org/0000-0001-6187-1684"},"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":"Goutam Saha","raw_affiliation_strings":["IIT Kharagpur,Dept. of Electronics & Electrical Communication Engineering,West Bengal,India"],"affiliations":[{"raw_affiliation_string":"IIT Kharagpur,Dept. of Electronics & Electrical Communication Engineering,West Bengal,India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.04563616,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9724000096321106,"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/T12151","display_name":"Interpreting and Communication in Healthcare","score":0.9416000247001648,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.8157557845115662},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8004937767982483},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6704921722412109},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6277726888656616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6036211252212524},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5990227460861206},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5835813879966736},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.43917837738990784},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3453769087791443},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1394057273864746}],"concepts":[{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.8157557845115662},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004937767982483},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6704921722412109},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6277726888656616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6036211252212524},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5990227460861206},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5835813879966736},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.43917837738990784},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3453769087791443},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1394057273864746},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ncc63735.2025.10983901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc63735.2025.10983901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 National Conference on Communications (NCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1487999662","https://openalex.org/W2074619556","https://openalex.org/W2091409162","https://openalex.org/W2100379591","https://openalex.org/W2103523269","https://openalex.org/W2104457544","https://openalex.org/W2895547158","https://openalex.org/W3010120876","https://openalex.org/W3024869864","https://openalex.org/W3097777922","https://openalex.org/W3198429080","https://openalex.org/W3213029956","https://openalex.org/W4385823025","https://openalex.org/W4392903482","https://openalex.org/W4401752664","https://openalex.org/W4404178731","https://openalex.org/W6779919476"],"related_works":["https://openalex.org/W226586525","https://openalex.org/W2924380321","https://openalex.org/W2962716343","https://openalex.org/W2765804957","https://openalex.org/W178568469","https://openalex.org/W4386302218","https://openalex.org/W3153972594","https://openalex.org/W43702919","https://openalex.org/W2362145681","https://openalex.org/W2913520953"],"abstract_inverted_index":{"This":[0],"study":[1],"investigates":[2],"the":[3,18,32,47,63,67,81,109,116,151,165,171],"effectiveness":[4],"of":[5,66,164,173],"various":[6],"features":[7,60,94],"and":[8,21,144,157],"state-of-the-art":[9,104],"spoken":[10],"language":[11,110,119],"identification":[12],"(LID)":[13],"systems":[14],"in":[15,76],"quantitatively":[16],"analyzing":[17],"classification":[19,52],"performances":[20],"confusions":[22],"across":[23],"languages.":[24],"We":[25,85],"focus":[26],"on":[27],"23":[28],"Indian":[29],"languages":[30],"from":[31,62],"IIITH-ILSC":[33],"corpus":[34],"for":[35],"our":[36,88,148],"analysis.":[37],"Initially,":[38],"we":[39,54,106,133],"employ":[40],"conventional":[41],"mel-frequency":[42],"cepstral":[43],"coefficients":[44],"(MFCCs)":[45],"with":[46,140],"ECAPA-TDNN":[48],"classifier.":[49],"To":[50,123,147],"enhance":[51],"performance,":[53],"further":[55,86,124],"implement":[56],"self-supervised":[57,153],"learning":[58,154],"(SSL)-based":[59,155],"derived":[61],"transformer":[64],"layers":[65],"wav2vec":[68,92],"2.0":[69,93],"XLSR":[70],"model,":[71],"observing":[72],"a":[73,96],"substantial":[74],"improvement":[75],"accuracy,":[77],"(90.73%)":[78],"compared":[79],"to":[80,95,113],"MFCC-based":[82],"model":[83],"(72.86%).":[84],"expand":[87],"approach":[89],"by":[90],"applying":[91],"recently":[97],"proposed":[98],"conformer-based":[99],"architecture.":[100],"For":[101],"all":[102],"these":[103,127],"systems,":[105],"then":[107],"compare":[108],"confusion":[111,129],"patterns":[112,130],"check":[114],"if":[115],"most":[117],"confusing":[118],"pairs":[120],"remain":[121],"consistent.":[122],"examine":[125],"whether":[126],"obtained":[128],"are":[131],"framework-dependent,":[132],"perform":[134],"comparative":[135],"analyses":[136],"among":[137],"LID":[138,174],"frameworks":[139],"multiple":[141],"best-performing":[142],"checkpoints":[143],"random":[145],"initializations.":[146],"knowledge,":[149],"using":[150],"pre-trained":[152],"representations":[156],"large-scale":[158],"DNN-based":[159],"classifiers,":[160],"this":[161],"is":[162],"one":[163],"first":[166],"studies":[167],"that":[168],"explicitly":[169],"explore":[170],"interpretability":[172],"frameworks.":[175]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}