{"id":"https://openalex.org/W2086820606","doi":"https://doi.org/10.1109/icassp.2013.6638316","title":"Soft nonnegative matrix co-factorizationwith application to multimodal speaker diarization","display_name":"Soft nonnegative matrix co-factorizationwith application to multimodal speaker diarization","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2086820606","doi":"https://doi.org/10.1109/icassp.2013.6638316","mag":"2086820606"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638316","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638316","pdf_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6638316","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6638316","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068887439","display_name":"Nicolas Seichepine","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"N. Seichepine","raw_affiliation_strings":["Institut Mines-T\u00e9l\u00e9com, CNRS LTCI, T\u00e9l\u00e9com ParisTech, France","[LTCI, Telecom Paristech, Paris, France]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Mines-T\u00e9l\u00e9com, CNRS LTCI, T\u00e9l\u00e9com ParisTech, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I205703379","https://openalex.org/I4210165912"]},{"raw_affiliation_string":"[LTCI, Telecom Paristech, Paris, France]","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060031161","display_name":"Slim Essid","orcid":"https://orcid.org/0000-0002-0028-327X"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"S. Essid","raw_affiliation_strings":["Institut Mines-T\u00e9l\u00e9com, CNRS LTCI, T\u00e9l\u00e9com ParisTech, France","[LTCI, Telecom Paristech, Paris, France]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Mines-T\u00e9l\u00e9com, CNRS LTCI, T\u00e9l\u00e9com ParisTech, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I205703379","https://openalex.org/I4210165912"]},{"raw_affiliation_string":"[LTCI, Telecom Paristech, Paris, France]","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022368934","display_name":"C\u00e9dric F\u00e9votte","orcid":"https://orcid.org/0000-0003-3801-5534"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I201841394","display_name":"Universit\u00e9 C\u00f4te d'Azur","ror":"https://ror.org/019tgvf94","country_code":"FR","type":"education","lineage":["https://openalex.org/I201841394"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C. Fevotte","raw_affiliation_strings":["Laboratoire Lagrange, CNRS, OCA, University of Nice, France","Lab. Lagrange, Univ. of Nice, Nice, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire Lagrange, CNRS, OCA, University of Nice, France","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Lab. Lagrange, Univ. of Nice, Nice, France","institution_ids":["https://openalex.org/I201841394"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105628617","display_name":"Olivier Capp\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"O. Cappe","raw_affiliation_strings":["CNRS LTCI, T\u00e9l\u00e9com ParisTech, France","[LTCI, Telecom Paristech, Paris, France]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS LTCI, T\u00e9l\u00e9com ParisTech, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I4210165912"]},{"raw_affiliation_string":"[LTCI, Telecom Paristech, Paris, France]","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2472,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.83888143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3537","last_page":"3541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9962999820709229,"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/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8233399391174316},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.7278906106948853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6887242197990417},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6425776481628418},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5875451564788818},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5763009786605835},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4889296591281891},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4466615915298462},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43775612115859985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4372522532939911},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4240211248397827},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3442147970199585},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29076921939849854}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8233399391174316},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.7278906106948853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6887242197990417},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6425776481628418},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5875451564788818},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5763009786605835},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4889296591281891},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4466615915298462},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43775612115859985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4372522532939911},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4240211248397827},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3442147970199585},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29076921939849854},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6638316","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638316","pdf_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6638316","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02943543v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02943543","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2013 - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2013, Vancouver, France. pp.3537-3541, &#x27E8;10.1109/ICASSP.2013.6638316&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1109/icassp.2013.6638316","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638316","pdf_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6638316","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W59193195","https://openalex.org/W1614862348","https://openalex.org/W1971791733","https://openalex.org/W1990231296","https://openalex.org/W1999031685","https://openalex.org/W2069214509","https://openalex.org/W2081074144","https://openalex.org/W2083667973","https://openalex.org/W2112039577","https://openalex.org/W2114508388","https://openalex.org/W2120575676","https://openalex.org/W2130295778","https://openalex.org/W2149414429","https://openalex.org/W2159094433","https://openalex.org/W2161077892","https://openalex.org/W2247585390","https://openalex.org/W2398758317","https://openalex.org/W3209042722","https://openalex.org/W6602402129"],"related_works":["https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W34555840","https://openalex.org/W2146544734"],"abstract_inverted_index":{"This":[0,12],"paper":[1],"presents":[2],"a":[3,39,95],"new":[4],"method":[5,13,103],"for":[6,38,59],"bimodal":[7],"nonnegative":[8],"matrix":[9],"factorization":[10],"(NMF).":[11],"is":[14,63,80,92,104],"well-suited":[15],"to":[16,29],"situations":[17],"where":[18],"two":[19],"streams":[20],"of":[21,101],"data":[22,68],"are":[23,27],"concurrently":[24],"analyzed":[25],"and":[26,109,122],"expected":[28],"be":[30],"related":[31,69],"by":[32],"loosely":[33],"common":[34],"factors.":[35],"It":[36],"allows":[37],"soft":[40],"co-factorization,":[41],"which":[42],"takes":[43],"into":[44],"account":[45],"the":[46,51,67,75,87,102,118],"relationship":[47],"that":[48,66,84,116],"exists":[49],"between":[50,120],"modalities":[52,124],"being":[53],"processed,":[54],"but":[55],"returns":[56],"different":[57],"factors":[58],"distinct":[60],"modalities.":[61],"There":[62],"no":[64,82],"need":[65,83],"with":[70],"each":[71],"modality":[72],"live":[73],"in":[74,125],"same":[76,88],"feature":[77],"space;":[78],"there":[79],"also":[81],"they":[85],"have":[86],"dimensionality.":[89],"The":[90,99],"co-factorization":[91],"obtained":[93],"via":[94],"majorization-minimization":[96],"(MM)":[97],"algorithm.":[98],"behavior":[100],"illustrated":[105],"on":[106],"both":[107],"synthetic":[108],"real-world":[110],"data.":[111],"In":[112],"particular,":[113],"we":[114],"show":[115],"exploiting":[117],"correlation":[119],"audio":[121],"video":[123],"edited":[126],"talk-show":[127],"videos":[128],"improve":[129],"speaker":[130],"diarization":[131],"results.":[132]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
