{"id":"https://openalex.org/W4406461691","doi":"https://doi.org/10.1109/slt61566.2024.10832221","title":"Inx-Speakerhub: A 2000-Hour Indian Multiligual Speaker Verification Corpus","display_name":"Inx-Speakerhub: A 2000-Hour Indian Multiligual Speaker Verification Corpus","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461691","doi":"https://doi.org/10.1109/slt61566.2024.10832221"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5063735369","display_name":"N J Metilda Sagaya Mary","orcid":"https://orcid.org/0000-0001-6931-4030"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"N J Metilda Sagaya Mary","raw_affiliation_strings":["Indian Institute of Technology Madras,SPRING Lab,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras,SPRING Lab,India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S Umesh","raw_affiliation_strings":["Indian Institute of Technology Madras,SPRING Lab,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras,SPRING Lab,India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5063735369"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23808496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1217","last_page":"1223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9948999881744385,"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/computer-science","display_name":"Computer science","score":0.6625617742538452},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.616511344909668},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6024665832519531},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40490126609802246},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.35545629262924194}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6625617742538452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.616511344909668},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6024665832519531},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40490126609802246},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.35545629262924194}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2748488820","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2981087920","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3095877226","https://openalex.org/W4205234379","https://openalex.org/W4385823419","https://openalex.org/W4392902963","https://openalex.org/W4402111364","https://openalex.org/W6850402104"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,13,40,46,74,124,135,149,152,163],"data":[4,79],"collection":[5],"efforts,":[6],"statistics":[7],"and":[8,85,105],"preparation":[9],"involved":[10],"in":[11,33,51,80,91,146,156],"creating":[12,113],"2333-hour":[14],"INX-SpeakerHub,":[15],"an":[16],"Indian":[17,30,36,69,77,95,125,157],"multilingual":[18],"speaker":[19,59,120,153,164],"identification":[20],"dataset.":[21],"It":[22],"has":[23,44,138],"legally":[24],"collected":[25],"speech":[26,71,92],"from":[27],"approximately":[28],"11,000":[29],"native":[31],"speakers":[32],"10":[34],"different":[35,168],"languages.":[37,96,158,176],"Until":[38],"now,":[39],"VoxCeleb":[41,57,81,136],"dataset":[42,115,137],"(1+2)":[43],"been":[45],"most":[47],"popular":[48],"corpus":[49],"used":[50,64],"many":[52],"current":[53],"state-of-theart":[54],"systems.":[55],"Therefore,":[56],"based":[58],"embedding":[60,121],"extractors":[61,122],"are":[62],"often":[63],"by":[65],"default":[66],"even":[67],"for":[68,123,151],"language-based":[70],"applications.":[72],"However,":[73],"proportion":[75],"of":[76,128],"language":[78,169],"is":[82,98,106,127],"quite":[83],"less":[84],"might":[86],"lead":[87],"to":[88,108,118,148],"subpar":[89],"performance":[90,166],"tasks":[93],"involving":[94],"India":[97],"a":[99,114],"country":[100],"with":[101],"22":[102],"official":[103],"languages":[104,126],"home":[107],"1.43":[109],"billion":[110],"people.":[111],"So":[112],"like":[116],"INX-SpeakerHub":[117,150],"build":[119],"great":[129],"interest.":[130],"As":[131],"our":[132],"analysis":[133],"shows,":[134],"higher":[139],"%":[140],"equal":[141],"error":[142],"rate":[143],"(%":[144],"EER)":[145],"comparison":[147],"verification":[154,165],"task":[155],"Further,":[159],"we":[160],"also":[161],"analyse":[162],"across":[167],"families":[170],"as":[171,173],"well":[172],"on":[174],"unseen":[175]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}