{"id":"https://openalex.org/W1998280908","doi":"https://doi.org/10.1109/asru.2007.4430198","title":"Multiple feature combination to improve speaker diarization of telephone conversations","display_name":"Multiple feature combination to improve speaker diarization of telephone conversations","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W1998280908","doi":"https://doi.org/10.1109/asru.2007.4430198","mag":"1998280908"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","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/A5114009216","display_name":"Vishwa Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vishwa Gupta","raw_affiliation_strings":["Centre de Recherche Informatique de Montreal","Centre de recherche informatique de Montreal, Montreal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre de Recherche Informatique de Montreal","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"Centre de recherche informatique de Montreal, Montreal","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036466893","display_name":"Patrick Kenny","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Patrick Kenny","raw_affiliation_strings":["Centre de Recherche Informatique de Montreal","Centre de recherche informatique de Montreal, Montreal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre de Recherche Informatique de Montreal","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"Centre de recherche informatique de Montreal, Montreal","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061517549","display_name":"Pierre Ouellet","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pierre Ouellet","raw_affiliation_strings":["Centre de Recherche Informatique de Montreal","Centre de recherche informatique de Montreal, Montreal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre de Recherche Informatique de Montreal","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"Centre de recherche informatique de Montreal, Montreal","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079352923","display_name":"Gilles Boulianne","orcid":"https://orcid.org/0000-0001-9383-6189"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gilles Boulianne","raw_affiliation_strings":["Centre de Recherche Informatique de Montreal","Centre de recherche informatique de Montreal, Montreal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre de Recherche Informatique de Montreal","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"Centre de recherche informatique de Montreal, Montreal","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034083532","display_name":"Pierre Dumouchel","orcid":"https://orcid.org/0000-0001-5584-4428"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pierre Dumouchel","raw_affiliation_strings":["Centre de Recherche Informatique de Montreal","Centre de recherche informatique de Montreal, Montreal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre de Recherche Informatique de Montreal","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"Centre de recherche informatique de Montreal, Montreal","institution_ids":["https://openalex.org/I4210111842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210111842"],"apc_list":null,"apc_paid":null,"fwci":2.4217,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.89714292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"705","last_page":"710"},"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":0.9976999759674072,"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":0.9851999878883362,"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":0.8395671844482422},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.8072007894515991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7302271127700806},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6720761656761169},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6681437492370605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5844013690948486},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5837477445602417},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.577843189239502},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5487565994262695},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.5346443057060242},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49948740005493164},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4668387174606323},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.448818564414978},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4355948269367218},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42946863174438477},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3550436496734619}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8395671844482422},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.8072007894515991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7302271127700806},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6720761656761169},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6681437492370605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5844013690948486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5837477445602417},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.577843189239502},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5487565994262695},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.5346443057060242},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49948740005493164},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4668387174606323},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.448818564414978},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4355948269367218},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42946863174438477},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3550436496734619},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2007.4430198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.153.3206","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.3206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.crim.ca/Publications/2007/documents/plein_texte/PAR_GupVals_ASRU2007.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W99811769","https://openalex.org/W2001936727","https://openalex.org/W2023466863","https://openalex.org/W2052269122","https://openalex.org/W2118313846","https://openalex.org/W2132990350","https://openalex.org/W2159591770","https://openalex.org/W2166980079","https://openalex.org/W2170695863","https://openalex.org/W2397634864","https://openalex.org/W6604061051","https://openalex.org/W6712325649"],"related_works":["https://openalex.org/W2119836628","https://openalex.org/W2206035908","https://openalex.org/W2356325859","https://openalex.org/W106647055","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2157299333"],"abstract_inverted_index":{"We":[0,84],"report":[1],"results":[2],"on":[3,190,196],"speaker":[4,10,55],"diarization":[5,11,78],"of":[6,28],"telephone":[7,156,172],"conversations.":[8],"This":[9],"process":[12],"is":[13,72,188],"similar":[14],"to":[15,143],"the":[16,77,100,121,132,148,162,177,191,197],"multistage":[17,87],"segmentation":[18,88],"and":[19,59,74,89,107,111,194],"clustering":[20,42,52,90],"system":[21],"used":[22,102,123],"in":[23,103,124,137,147],"broadcast":[24],"news.":[25],"It":[26],"consists":[27],"an":[29],"initial":[30],"acoustic":[31],"change":[32],"point":[33],"detection":[34],"algorithm,":[35],"iterative":[36],"Viterbi":[37,60,68,108],"re-segmentation,":[38],"gender":[39,104],"labeling,":[40,105],"agglomerative":[41,51],"using":[43,53,62,70],"a":[44,138,144,151],"Bayesian":[45],"information":[46],"criterion":[47],"(BIC),":[48],"followed":[49],"by":[50,82,164,179],"state-of-the-art":[54],"identification":[56],"methods":[57],"(SID)":[58],"re-segmentation":[61,69,109],"Gaussian":[63],"mixture":[64],"models":[65],"(GMMs).":[66],"The":[67,128,181],"GMMs":[71,101,122],"new,":[73],"it":[75],"reduces":[76],"error":[79,183],"rate":[80,184],"(DER)":[81],"10%.":[83],"repeat":[85],"these":[86,125],"steps":[91],"twice:":[92],"once":[93],"with":[94,114],"MFCCs":[95,116],"as":[96,117],"feature":[97,118],"parameters":[98,119],"for":[99,120],"SID":[106],"steps,":[110],"another":[112,167],"time":[113],"Gaussianized":[115],"three":[126],"steps.":[127],"resulting":[129],"clusters":[130],"from":[131],"parallel":[133],"runs":[134],"are":[135],"combined":[136],"novel":[139],"way":[140],"that":[141],"leads":[142],"significant":[145],"reduction":[146],"DER.":[149],"On":[150,166],"development":[152,192],"set":[153,169],"containing":[154,170],"30":[155,171],"conversations,":[157,173],"this":[158,174],"combination":[159],"step":[160,175],"reduced":[161,176],"DER":[163,178],"20%.":[165],"test":[168,198],"13%.":[180],"best":[182],"we":[185],"have":[186],"achieved":[187],"6.7%":[189],"set,":[193],"9.0%":[195],"set.":[199]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}