{"id":"https://openalex.org/W3092655842","doi":"https://doi.org/10.1109/taslp.2020.3036231","title":"Novel Architectures for Unsupervised Information Bottleneck Based Speaker Diarization of Meetings","display_name":"Novel Architectures for Unsupervised Information Bottleneck Based Speaker Diarization of Meetings","publication_year":2020,"publication_date":"2020-11-05","ids":{"openalex":"https://openalex.org/W3092655842","doi":"https://doi.org/10.1109/taslp.2020.3036231","mag":"3092655842"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3036231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3036231","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.06304","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nauman Dawalatabad","orcid":"https://orcid.org/0000-0003-1592-6300"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nauman Dawalatabad","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Madras, Chennai, India"],"raw_orcid":"https://orcid.org/0000-0003-1592-6300","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Srikanth Madikeri","orcid":"https://orcid.org/0000-0002-4361-784X"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Srikanth Madikeri","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-4361-784X","affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":null,"display_name":"C. Chandra Sekhar","orcid":"https://orcid.org/0000-0001-5551-4883"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. Chandra Sekhar","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Madras, Chennai, India"],"raw_orcid":"https://orcid.org/0000-0001-5551-4883","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hema A. Murthy","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hema A. Murthy","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Madras, Chennai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8042,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.79563649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"14","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8618999719619751,"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":0.8618999719619751,"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":0.018799999728798866,"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/T12031","display_name":"Speech and dialogue systems","score":0.013000000268220901,"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/discriminative-model","display_name":"Discriminative model","score":0.8410000205039978},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8167999982833862},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7573000192642212},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.699999988079071},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5350000262260437},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5192999839782715},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5038999915122986},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.4397999942302704}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8410000205039978},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8167999982833862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781499981880188},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7573000192642212},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.699999988079071},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6158000230789185},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5350000262260437},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5192999839782715},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4729999899864197},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.4397999942302704},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.28360000252723694},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2020.3036231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3036231","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2010.06304","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.06304","pdf_url":"https://arxiv.org/pdf/2010.06304","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.06304","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.06304","pdf_url":"https://arxiv.org/pdf/2010.06304","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7557641143","display_name":null,"funder_award_id":"CSE1314142DRDOHEMA","funder_id":"https://openalex.org/F4320321024","funder_display_name":"Defence Research and Development Organisation"}],"funders":[{"id":"https://openalex.org/F4320321024","display_name":"Defence Research and Development Organisation","ror":"https://ror.org/05k37v296"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1873003601","https://openalex.org/W1963976507","https://openalex.org/W1965819578","https://openalex.org/W1996198360","https://openalex.org/W2010114458","https://openalex.org/W2038162002","https://openalex.org/W2069448468","https://openalex.org/W2069642050","https://openalex.org/W2081074144","https://openalex.org/W2098726438","https://openalex.org/W2104077623","https://openalex.org/W2120113977","https://openalex.org/W2121812409","https://openalex.org/W2125336414","https://openalex.org/W2148613904","https://openalex.org/W2513973755","https://openalex.org/W2515869040","https://openalex.org/W2518112949","https://openalex.org/W2638067502","https://openalex.org/W2746710273","https://openalex.org/W2748026385","https://openalex.org/W2750259098","https://openalex.org/W2753324760","https://openalex.org/W2888975288","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2902864383","https://openalex.org/W2915548730","https://openalex.org/W2937267585","https://openalex.org/W2962788625","https://openalex.org/W2963227667","https://openalex.org/W2963470929","https://openalex.org/W2963702081","https://openalex.org/W2963745998","https://openalex.org/W2963962398","https://openalex.org/W2964052309","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W6605762983","https://openalex.org/W6631943919","https://openalex.org/W6634840827","https://openalex.org/W6636488977","https://openalex.org/W6637108112","https://openalex.org/W6637485440","https://openalex.org/W6644167626","https://openalex.org/W6696885005","https://openalex.org/W6766978945","https://openalex.org/W6947841180"],"related_works":[],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,49,70,116,132],"is":[2,7,10,26,79,154,206,248],"an":[3,227],"important":[4],"problem":[5],"that":[6,118,224,239],"topical,":[8],"and":[9,40,90,176,220,246,253],"especially":[11],"useful":[12],"as":[13,75],"a":[14,58,92,109,151,171,240],"preprocessor":[15],"for":[16,64,96],"conversational":[17],"speech":[18],"related":[19],"applications.":[20],"The":[21,128,160,180],"objective":[22],"of":[23,55,104,126,147,200,216,244],"this":[24],"article":[25],"two-fold:":[27],"(i)":[28],"segment":[29,61,204,218],"initialization":[30,62,82,205,219],"by":[31],"uniformly":[32,86],"distributing":[33],"speaker":[34,43,69,84,115,120,131,167,194,221],"information":[35,78,85],"across":[36,87],"the":[37,47,52,56,76,88,101,105,124,138,144,148,187,192,197,201,209,214,251],"initial":[38],"segments,":[39],"(ii)":[41],"incorporating":[42],"discriminative":[44,121,168,181,222],"features":[45,122,169,182,223],"within":[46],"unsupervised":[48],"framework.":[50,211],"In":[51,100,196],"first":[53,145],"part":[54,103,199],"work,":[57,106],"varying":[59],"length":[60],"technique":[63],"Information":[65,111],"Bottleneck":[66,112],"(IB)":[67],"based":[68,98,114,130,141,158],"system":[71,117,133],"using":[72,156,170],"phoneme":[73],"rate":[74],"side":[77],"proposed.":[80],"This":[81,212],"distributes":[83],"segments":[89],"provides":[91],"better":[93,217],"starting":[94],"point":[95],"IB":[97,140,157],"clustering.":[99,159],"second":[102,188],"we":[107],"present":[108],"Two-Pass":[110],"(TPIB)":[113],"incorporates":[119],"during":[123],"process":[125],"diarization.":[127],"TPIB":[129,149,210],"has":[134],"shown":[135],"improvement":[136,229,243],"over":[137],"baseline":[139],"system.":[142],"During":[143],"pass":[146,189],"system,":[150],"coarse":[152],"segmentation":[153],"performed":[155],"alignments":[161],"obtained":[162,183,249],"are":[163,184],"used":[164,185],"to":[165,190],"generate":[166],"shallow":[172],"feed-forward":[173],"neural":[174],"network":[175],"linear":[177],"discriminant":[178],"analysis.":[179],"in":[186,226,230],"obtain":[191],"final":[193,198],"boundaries.":[195],"paper,":[202],"variable":[203],"combined":[207],"with":[208],"leverages":[213],"advantages":[215],"results":[225],"additional":[228],"performance.":[231],"An":[232],"evaluation":[233],"on":[234,250],"standard":[235],"meeting":[236],"datasets":[237],"shows":[238],"significant":[241],"absolute":[242],"3.9%":[245],"4.7%":[247],"NIST":[252],"AMI":[254],"datasets,":[255],"respectively.":[256]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2020-10-22T00:00:00"}