{"id":"https://openalex.org/W2961166387","doi":"https://doi.org/10.21437/interspeech.2019-1102","title":"Toeplitz Inverse Covariance Based Robust Speaker Clustering for Naturalistic Audio Streams","display_name":"Toeplitz Inverse Covariance Based Robust Speaker Clustering for Naturalistic Audio Streams","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2961166387","doi":"https://doi.org/10.21437/interspeech.2019-1102","mag":"2961166387"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1102","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.05584","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033701513","display_name":"Harishchandra Dubey","orcid":"https://orcid.org/0000-0003-0476-3884"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harishchandra Dubey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111469714","display_name":"Abhijeet Sangwan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhijeet Sangwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07323404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"416","last_page":"420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9977999925613403,"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":0.9977999925613403,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6772266030311584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6203278303146362},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5115955471992493},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48552465438842773},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48325616121292114},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.47585293650627136},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.458456426858902},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.45818865299224854},{"id":"https://openalex.org/keywords/toeplitz-matrix","display_name":"Toeplitz matrix","score":0.4530652165412903},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.4389892816543579},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42908287048339844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3931613564491272},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2858148217201233},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2733108401298523},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1146695613861084}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6772266030311584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6203278303146362},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5115955471992493},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48552465438842773},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48325616121292114},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.47585293650627136},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.458456426858902},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.45818865299224854},{"id":"https://openalex.org/C147710293","wikidata":"https://www.wikidata.org/wiki/Q849428","display_name":"Toeplitz matrix","level":2,"score":0.4530652165412903},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.4389892816543579},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42908287048339844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3931613564491272},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2858148217201233},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2733108401298523},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1146695613861084},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-1102","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.05584","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.05584","pdf_url":"https://arxiv.org/pdf/1907.05584","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},{"id":"mag:2961166387","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1907.05584","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1907.05584","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.05584","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.05584","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.05584","pdf_url":"https://arxiv.org/pdf/1907.05584","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2961166387.pdf","grobid_xml":"https://content.openalex.org/works/W2961166387.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1516414061","https://openalex.org/W1569447338","https://openalex.org/W1583620810","https://openalex.org/W1936725236","https://openalex.org/W2052269122","https://openalex.org/W2060656758","https://openalex.org/W2063511145","https://openalex.org/W2081074144","https://openalex.org/W2086086554","https://openalex.org/W2093499222","https://openalex.org/W2121415728","https://openalex.org/W2125642021","https://openalex.org/W2150769028","https://openalex.org/W2395750323","https://openalex.org/W2481304079","https://openalex.org/W2541334028","https://openalex.org/W2556948255","https://openalex.org/W2588638982","https://openalex.org/W2626473047","https://openalex.org/W2800837202","https://openalex.org/W2801018181","https://openalex.org/W2805960464","https://openalex.org/W2810313973","https://openalex.org/W2895902173","https://openalex.org/W2899894342","https://openalex.org/W2937267585","https://openalex.org/W2962708786","https://openalex.org/W2962788616","https://openalex.org/W2963947576","https://openalex.org/W3098028374","https://openalex.org/W4301688325"],"related_works":["https://openalex.org/W2972371226","https://openalex.org/W2886403805","https://openalex.org/W2038101708","https://openalex.org/W2538493831","https://openalex.org/W2153342002","https://openalex.org/W2482731677","https://openalex.org/W1505639203","https://openalex.org/W2115861008","https://openalex.org/W1873003601","https://openalex.org/W1519129566","https://openalex.org/W2017552746","https://openalex.org/W2549969819","https://openalex.org/W2901446417","https://openalex.org/W3015778863","https://openalex.org/W2340557458","https://openalex.org/W1998280908","https://openalex.org/W2035330378","https://openalex.org/W1966142845","https://openalex.org/W2001936727","https://openalex.org/W2155680790"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,116,174],"determines":[2],"who":[3],"spoke":[4],"and":[5,107,134,137,146,162,195,202],"when?":[6],"in":[7,50,85,173],"an":[8,86],"audio":[9,87],"stream.":[10,88],"In":[11],"this":[12,38],"study,":[13],"we":[14,53],"propose":[15],"a":[16,41],"model-based":[17],"approach":[18],"for":[19,66,99,178],"robust":[20],"speaker":[21,33,79,84,140,148],"clustering":[22,149],"using":[23,103,183],"i-vectors.":[24],"The":[25],"ivectors":[26],"extracted":[27],"from":[28],"different":[29],"segments":[30],"of":[31,75,91,112,167],"same":[32,83],"are":[34],"correlated.":[35],"We":[36,142],"model":[37],"correlation":[39,64],"with":[40],"Markov":[42],"Random":[43],"Field":[44],"(MRF)":[45],"network.":[46],"Leveraging":[47],"the":[48,62,72,108,168,184],"advancements":[49,186],"MRF":[51,63],"modeling,":[52],"used":[54],"Toeplitz":[55],"Inverse":[56],"Covariance":[57],"(TIC)":[58],"matrix":[59],"to":[60,82,189],"represent":[61],"network":[65],"each":[67],"speaker.":[68],"This":[69],"approaches":[70],"captures":[71],"sequential":[73],"structure":[74],"i-vectors":[76],"(or":[77],"equivalent":[78],"turns)":[80],"belonging":[81],"A":[89],"variant":[90],"standard":[92],"Expectation":[93],"Maximization":[94],"(EM)":[95],"algorithm":[96],"is":[97,156,181,200],"adopted":[98],"deriving":[100],"closed-form":[101],"solution":[102],"dynamic":[104],"programming":[105],"(DP)":[106],"alternating":[109],"direction":[110],"method":[111],"multiplier":[113],"(ADMM).":[114],"Our":[115,153],"system":[117],"has":[118],"four":[119],"steps:":[120],"(1)":[121],"ground-truth":[122],"segmentation;":[123],"(2)":[124],"i-vector":[125],"extraction;":[126],"(3)":[127],"post-processing":[128],"(mean":[129],"subtraction,":[130],"principal":[131],"component":[132],"analysis,":[133],"length-normalization)":[135],";":[136],"(4)":[138],"proposed":[139,185],"clustering.":[141],"employ":[143],"cosine":[144],"K-means":[145],"movMF":[147],"as":[150,187],"baseline":[151],"approaches.":[152],"evaluation":[154],"data":[155],"derived":[157],"from:":[158],"(i)":[159],"CRSS-PLTL":[160,179],"corpus,":[161],"(ii)":[163],"two":[164],"meetings":[165,193],"subset":[166],"AMI":[169,192],"corpus.":[170],"Relative":[171],"reduction":[172,199],"error":[175],"rate":[176],"(DER)":[177],"corpus":[180],"43.22%":[182],"compared":[188],"baseline.":[190],"For":[191],"IS1000a":[194],"IS1003b,":[196],"relative":[197],"DER":[198],"29.37%":[201],"9.21%,":[203],"respectively.":[204]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}