{"id":"https://openalex.org/W4406418132","doi":"https://doi.org/10.1109/tale62452.2024.10834319","title":"Advancing Speaker Diarization With Whisper Speech Recognition for Different Learning Environments","display_name":"Advancing Speaker Diarization With Whisper Speech Recognition for Different Learning Environments","publication_year":2024,"publication_date":"2024-12-09","ids":{"openalex":"https://openalex.org/W4406418132","doi":"https://doi.org/10.1109/tale62452.2024.10834319"},"language":"en","primary_location":{"id":"doi:10.1109/tale62452.2024.10834319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tale62452.2024.10834319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)","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/A5112844207","display_name":"A. R. Desai","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":"Aarsh Desai","raw_affiliation_strings":["Indian Institute of Information Technology Dharwad,Data Science and Artificial Intelligence,Dharwad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Dharwad,Data Science and Artificial Intelligence,Dharwad,India","institution_ids":["https://openalex.org/I26072440","https://openalex.org/I4210152718","https://openalex.org/I4387153068"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115939938","display_name":"N.V.J.K Kartik","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":"N. V. J. K Kartik","raw_affiliation_strings":["Indian Institute of Information Technology Dharwad,Data Science and Artificial Intelligence,Dharwad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Dharwad,Data Science and Artificial Intelligence,Dharwad,India","institution_ids":["https://openalex.org/I26072440","https://openalex.org/I4210152718","https://openalex.org/I4387153068"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Priyesh Gupta","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":"Priyesh Gupta","raw_affiliation_strings":["Indian Institute of Information Technology Dharwad,Data Science and Artificial Intelligence,Dharwad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Dharwad,Data Science and Artificial Intelligence,Dharwad,India","institution_ids":["https://openalex.org/I26072440","https://openalex.org/I4210152718","https://openalex.org/I4387153068"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112574613","display_name":"Vinayak Vinayak","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":"Vinayak","raw_affiliation_strings":["Indian Institute of Information Technology Dharwad,Data Science and Artificial Intelligence,Dharwad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Dharwad,Data Science and Artificial Intelligence,Dharwad,India","institution_ids":["https://openalex.org/I26072440","https://openalex.org/I4210152718","https://openalex.org/I4387153068"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076771617","display_name":"T. S. Ashwin","orcid":null},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashwin T S","raw_affiliation_strings":["Vanderbilt University,Computer Science,Tennessee,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Computer Science,Tennessee,USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017587934","display_name":"Manjunath K Vanahalli","orcid":"https://orcid.org/0000-0003-3677-6276"},"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":"Manjunath K. Vanahalli","raw_affiliation_strings":["Indian Institute of Information Technology Dharwad,Data Science and Artificial Intelligence,Dharwad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Dharwad,Data Science and Artificial Intelligence,Dharwad,India","institution_ids":["https://openalex.org/I26072440","https://openalex.org/I4210152718","https://openalex.org/I4387153068"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022686050","display_name":"Ramkumar Rajendran","orcid":"https://orcid.org/0000-0002-0411-1782"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ramkumar Rajendran","raw_affiliation_strings":["Indian Institute of Technology Bombay,Educational Technology,Mumbai,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay,Educational Technology,Mumbai,India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61230642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9984999895095825,"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":0.9947999715805054,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.7990434169769287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7803172469139099},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6521877646446228},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6043104529380798}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7990434169769287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803172469139099},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6521877646446228},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6043104529380798}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tale62452.2024.10834319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tale62452.2024.10834319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2114443541","https://openalex.org/W2122575992","https://openalex.org/W2153727825","https://openalex.org/W2525821395","https://openalex.org/W2605474091","https://openalex.org/W2726515241","https://openalex.org/W2890964092","https://openalex.org/W2928165649","https://openalex.org/W2948572500","https://openalex.org/W2980547949","https://openalex.org/W2998565858","https://openalex.org/W3011982558","https://openalex.org/W3024869864","https://openalex.org/W3093501662","https://openalex.org/W3162347631","https://openalex.org/W3184730666","https://openalex.org/W3212886388","https://openalex.org/W4211120555","https://openalex.org/W4221165517","https://openalex.org/W4285218990","https://openalex.org/W4321505178","https://openalex.org/W4383181014","https://openalex.org/W4383181303","https://openalex.org/W4385822293","https://openalex.org/W4385822356","https://openalex.org/W4387757490","https://openalex.org/W4396830593","https://openalex.org/W4399487970","https://openalex.org/W6678369638","https://openalex.org/W6847363464","https://openalex.org/W6854145563","https://openalex.org/W6854657433"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"This":[0,172],"study":[1,173],"investigates":[2],"the":[3,13,25,51,57,97,101,108,162,166,169,175],"application":[4],"of":[5,54,60,78,100,114,168,197],"speaker":[6,183],"diarization":[7,52,145,184],"methodologies":[8],"within":[9],"educational":[10,187],"contexts,":[11,139],"addressing":[12],"unique":[14],"linguistic":[15],"and":[16,30,71,88,125,151],"environmental":[17],"challenges":[18],"present":[19],"in":[20,137,185],"Indian":[21],"learning":[22,199],"environments.":[23],"Despite":[24],"frequent":[26],"switching":[27],"between":[28],"English":[29],"local":[31],"languages,":[32],"current":[33],"state-of-the-art":[34],"models":[35,180],"often":[36],"fail":[37],"to":[38,181],"accurately":[39],"process":[40],"these":[41],"multilingual":[42,138,186],"interactions.":[43,200],"To":[44],"bridge":[45],"this":[46],"gap,":[47],"we":[48],"propose":[49],"integrating":[50],"outputs":[53],"Pyannote.audio":[55],"with":[56],"transcription":[58],"capabilities":[59],"OpenAI\u2019s":[61],"Whisper":[62],"model,":[63],"alongside":[64],"a":[65,76,190],"custom":[66,128],"Voice":[67],"Activity":[68],"Detection":[69],"(VAD)":[70],"embedding":[72],"clustering":[73],"pipeline.":[74],"Using":[75],"dataset":[77],"137":[79],"recordings":[80],"from":[81],"an":[82,89],"online":[83],"Human-Computer":[84],"Interaction":[85],"(HCI)":[86],"course":[87],"augmented":[90],"reality":[91],"(AR)":[92],"classroom,":[93],"our":[94],"findings":[95],"highlight":[96],"enhanced":[98],"performance":[99],"proposed":[102,163],"methodologies.":[103],"The":[104,127],"Pyannote-Whisper":[105],"pipeline":[106],"achieved":[107],"lowest":[109],"Diarization":[110],"Error":[111],"Rate":[112],"(DER)":[113],"0.26,":[115],"outperforming":[116],"other":[117],"models,":[118,164],"including":[119],"commercial":[120],"applications":[121],"such":[122],"as":[123],"Deepgram":[124],"Otter.":[126],"VAD":[129],"+":[130],"Embedding":[131],"Clustering":[132],"Pipeline":[133],"also":[134],"demonstrated":[135],"robustness":[136,167],"showcasing":[140],"its":[141],"potential":[142,176],"for":[143,177],"accurate":[144],"without":[146],"relying":[147],"on":[148],"transcription.":[149],"Fine-tuning":[150],"hyperparameter":[152],"optimization":[153],"were":[154],"performed,":[155],"yet":[156],"did":[157],"not":[158],"significantly":[159],"improve":[160,182],"upon":[161],"indicating":[165],"initial":[170],"approach.":[171],"underscores":[174],"adapting":[178],"existing":[179],"settings,":[188],"providing":[189],"significant":[191],"step":[192],"towards":[193],"more":[194],"robust":[195],"analysis":[196],"collaborative":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}