{"id":"https://openalex.org/W1963976507","doi":"https://doi.org/10.1109/tasl.2010.2048603","title":"An Information Theoretic Combination of MFCC and TDOA Features for Speaker Diarization","display_name":"An Information Theoretic Combination of MFCC and TDOA Features for Speaker Diarization","publication_year":2010,"publication_date":"2010-04-20","ids":{"openalex":"https://openalex.org/W1963976507","doi":"https://doi.org/10.1109/tasl.2010.2048603","mag":"1963976507"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2048603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2048603","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publications.idiap.ch/index.php/publications/showcite/Vijayasenan_Idiap-RR-22-2010","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080162701","display_name":"Deepu Vijayasenan","orcid":null},"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":"Deepu Vijayasenan","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061495800","display_name":"Fabio Valente","orcid":null},"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":"Fabio Valente","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"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":"Herv\u00e9 Bourlard","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":3.2144,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.91840066,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"19","issue":"2","first_page":"431","last_page":"438"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9980999827384949,"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":0.902319610118866},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.887447714805603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7488616108894348},{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.6950498819351196},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6564109325408936},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6189853549003601},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6141603589057922},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5909532308578491},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5130261778831482},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.46205320954322815},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42981988191604614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4067727029323578},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3362693190574646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09265092015266418}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.902319610118866},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.887447714805603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7488616108894348},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.6950498819351196},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6564109325408936},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6189853549003601},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6141603589057922},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5909532308578491},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5130261778831482},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.46205320954322815},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42981988191604614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4067727029323578},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3362693190574646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09265092015266418},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tasl.2010.2048603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2048603","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:infoscience.tind.io:155017","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/155017","pdf_url":"http://publications.idiap.ch/index.php/publications/showcite/Vijayasenan_Idiap-RR-22-2010","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":"research article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.376.5558","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.376.5558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/reports/2010/Vijayasenan_Idiap-RR-22-2010.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:150618","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/150618","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"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:155017","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/155017","pdf_url":"http://publications.idiap.ch/index.php/publications/showcite/Vijayasenan_Idiap-RR-22-2010","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":"research article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1963976507.pdf","grobid_xml":"https://content.openalex.org/works/W1963976507.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1482605500","https://openalex.org/W1524832141","https://openalex.org/W1556474518","https://openalex.org/W1557470594","https://openalex.org/W1558086160","https://openalex.org/W1592881709","https://openalex.org/W1686946872","https://openalex.org/W1876378865","https://openalex.org/W2070945723","https://openalex.org/W2098726438","https://openalex.org/W2103621378","https://openalex.org/W2106015547","https://openalex.org/W2113386290","https://openalex.org/W2140672401","https://openalex.org/W2159730002","https://openalex.org/W2169165592","https://openalex.org/W2171700247","https://openalex.org/W2338994564","https://openalex.org/W2571118946","https://openalex.org/W2915347754","https://openalex.org/W3129653033","https://openalex.org/W4214887259","https://openalex.org/W4285719527","https://openalex.org/W6628911050","https://openalex.org/W6633391268"],"related_works":["https://openalex.org/W2048014685","https://openalex.org/W1963976507","https://openalex.org/W2370972896","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162"],"abstract_inverted_index":{"This":[0],"correspondence":[1],"describes":[2],"a":[3,76],"novel":[4],"system":[5,56,80,128],"for":[6],"speaker":[7,91,94],"diarization":[8,55,79],"of":[9,16,23,29,70,137],"meetings":[10,118],"recordings":[11],"based":[12],"on":[13,86,117],"the":[14,30,54,60,73,104,110,122,126,130],"combination":[15,112],"acoustic":[17],"features":[18,38],"(MFCC)":[19],"and":[20,36,93],"time":[21],"delay":[22],"arrivals":[24],"(TDOAS).":[25],"The":[26],"first":[27],"part":[28],"paper":[31],"analyzes":[32],"differences":[33],"between":[34],"MFCC":[35],"TDOA":[37],"which":[39],"possess":[40],"completely":[41],"different":[42,61],"statistical":[43],"properties.":[44],"When":[45],"Gaussian":[46],"mixture":[47],"models":[48],"are":[49,97],"used,":[50],"experiments":[51],"reveal":[52,120],"that":[53,121],"is":[57,81,132],"sensitive":[58],"to":[59,101,108],"recording":[62,131],"scenarios":[63],"(i.e.,":[64],"meeting":[65],"rooms":[66],"with":[67,134],"varying":[68,135],"number":[69,136],"microphones).":[71],"In":[72],"second":[74],"part,":[75],"new":[77],"multistream":[78],"proposed":[82,105,123],"extending":[83],"previous":[84],"work":[85],"information":[87],"theoretic":[88],"diarization.":[89],"Both":[90],"clustering":[92],"realignment":[95],"steps":[96],"discussed;":[98],"in":[99],"contrary":[100],"current":[102],"systems,":[103],"method":[106],"avoids":[107],"perform":[109],"feature":[111],"averaging":[113],"log-likelihood":[114],"scores.":[115],"Experiments":[116],"data":[119],"approach":[124],"outperforms":[125],"GMM-based":[127],"when":[129],"done":[133],"microphones.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}