{"id":"https://openalex.org/W2518112949","doi":"https://doi.org/10.21437/interspeech.2016-714","title":"Two-Pass IB Based Speaker Diarization System Using Meeting-Specific ANN Based Features","display_name":"Two-Pass IB Based Speaker Diarization System Using Meeting-Specific ANN Based Features","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2518112949","doi":"https://doi.org/10.21437/interspeech.2016-714","mag":"2518112949"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-714","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/223746","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067313233","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":["Indian Institute of Technology Madras, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084521938","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, CH-1920 Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, CH-1920 Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113563423","display_name":"C. Chandra Sekhar","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":"C Chandra Sekhar","raw_affiliation_strings":["Indian Institute of Technology Madras, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032418366","display_name":"Hema A. Murthy","orcid":"https://orcid.org/0000-0003-3611-6550"},"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":["Indian Institute of Technology Madras, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, 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":0.3883,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60492917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2199","last_page":"2203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.9962000250816345,"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":0.8802537322044373},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.8358681797981262},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8331470489501953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7419381141662598},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7009382247924805},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6663110256195068},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5785837173461914},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.556244432926178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5510740876197815},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5351764559745789},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.5039054751396179},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49225011467933655},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42837095260620117}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8802537322044373},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8358681797981262},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8331470489501953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419381141662598},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7009382247924805},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6663110256195068},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5785837173461914},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.556244432926178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5510740876197815},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5351764559745789},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.5039054751396179},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49225011467933655},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42837095260620117},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2016-714","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:223746","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/223746","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:256334","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/256334","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/256334","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:223746","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/132079","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:223746","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/223746","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","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":20,"referenced_works":["https://openalex.org/W142991516","https://openalex.org/W1577891482","https://openalex.org/W1686946872","https://openalex.org/W1873003601","https://openalex.org/W1963976507","https://openalex.org/W1996198360","https://openalex.org/W2010114458","https://openalex.org/W2069448468","https://openalex.org/W2078169166","https://openalex.org/W2081074144","https://openalex.org/W2098726438","https://openalex.org/W2123237149","https://openalex.org/W2125336414","https://openalex.org/W2148613904","https://openalex.org/W2156255174","https://openalex.org/W2159591770","https://openalex.org/W2184045248","https://openalex.org/W2289985966","https://openalex.org/W2497516627","https://openalex.org/W4320013820"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W4245698648","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2405257913"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,137],"two-pass":[6],"Information":[7],"Bottleneck":[8],"(IB)":[9],"based":[10,22,27,46,105],"system":[11,30,106,121,128],"for":[12],"speaker":[13,28,35,132],"diarization":[14,29],"which":[15],"uses":[16],"meetingspecific":[17],"artificial":[18],"neural":[19],"network":[20],"(ANN)":[21],"features.We":[23,65],"first":[24],"use":[25],"IB":[26,104,127],"to":[31,53],"get":[32],"the":[33,58,63,68,72,93,98,102,119,125],"labelled":[34],"segments.These":[36],"segments":[37],"are":[38,89],"re-segmented":[39,59],"using":[40,57,101],"Kullback-Leibler":[41],"Hidden":[42],"Markov":[43],"Model":[44],"(KL-HMM)":[45],"re-segmentation.The":[47],"multi-layer":[48],"ANN":[49,74],"is":[50],"then":[51,66],"trained":[52,73],"discriminate":[54],"these":[55,82,86],"speakers":[56],"output":[60],"labels":[61],"and":[62,75,114,147],"spectral":[64,95],"extract":[67],"bottleneck":[69,87],"features":[70,88,96],"from":[71],"perform":[76],"principal":[77],"component":[78],"analysis":[79],"(PCA)":[80],"on":[81,111,149],"features.After":[83],"performing":[84],"PCA,":[85],"used":[90],"along":[91],"with":[92,107,136],"different":[94],"in":[97,129],"second":[99],"pass":[100],"same":[103],"KL-HMM":[108],"re-segmentation.Our":[109],"experiments":[110],"NIST":[112,150],"RT":[113],"AMI":[115,145],"datasets":[116,146],"show":[117],"that":[118],"proposed":[120],"performs":[122],"better":[123],"than":[124],"baseline":[126],"terms":[130],"of":[131,142],"error":[133],"rate":[134],"(SER)":[135],"best":[138],"case":[139],"relative":[140],"improvement":[141],"28.6%":[143],"amongst":[144],"27.1%":[148],"RT04eval":[151],"dataset.":[152]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}