{"id":"https://openalex.org/W140981554","doi":"https://doi.org/10.21437/interspeech.2004-425","title":"Adaptive classifier cascade for multimodal speaker identification","display_name":"Adaptive classifier cascade for multimodal speaker identification","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W140981554","doi":"https://doi.org/10.21437/interspeech.2004-425","mag":"140981554"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-425","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"conference-paper","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/A5064993025","display_name":"Engin Erzin","orcid":"https://orcid.org/0000-0002-2715-2368"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Engin Erzin","raw_affiliation_strings":["Koc\u00b8 University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Koc\u00b8 University","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074744284","display_name":"Y. Yemez","orcid":"https://orcid.org/0000-0002-7515-3138"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Yucel Yemez","raw_affiliation_strings":["Koc\u00b8 University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Koc\u00b8 University","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034648478","display_name":"A. Murat Tekalp","orcid":"https://orcid.org/0000-0003-1465-8121"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"A. Murat Tekalp","raw_affiliation_strings":["Koc\u00b8 University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Koc\u00b8 University","institution_ids":["https://openalex.org/I1351752"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1351752"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01334927,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2493","last_page":"2496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.983299970626831,"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/computer-science","display_name":"Computer science","score":0.7517892718315125},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6953527927398682},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6314631104469299},{"id":"https://openalex.org/keywords/cascading-classifiers","display_name":"Cascading classifiers","score":0.6310724020004272},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.6289839744567871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6135658025741577},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5627449154853821},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4771004319190979},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3925321698188782},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3861359655857086},{"id":"https://openalex.org/keywords/random-subspace-method","display_name":"Random subspace method","score":0.1892414689064026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7517892718315125},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6953527927398682},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6314631104469299},{"id":"https://openalex.org/C40651066","wikidata":"https://www.wikidata.org/wiki/Q5048220","display_name":"Cascading classifiers","level":4,"score":0.6310724020004272},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.6289839744567871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6135658025741577},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5627449154853821},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4771004319190979},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3925321698188782},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3861359655857086},{"id":"https://openalex.org/C106135958","wikidata":"https://www.wikidata.org/wiki/Q7291993","display_name":"Random subspace method","level":3,"score":0.1892414689064026},{"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-425","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2075306129","https://openalex.org/W2127884747","https://openalex.org/W2131402987","https://openalex.org/W2156404139","https://openalex.org/W2158275940","https://openalex.org/W2912341770"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,26,37,83],"multimodal":[3],"open-set":[4,69],"speaker":[5,70],"identification":[6,71],"system":[7],"that":[8,31,64,110,124],"integrates":[9],"information":[10],"coming":[11],"from":[12],"audio,":[13],"face":[14],"and":[15,98,104],"lip":[16],"motion":[17],"modalities.":[18],"For":[19],"fusion":[20],"of":[21,39,43,56,82,95,119],"multiple":[22],"modalities,":[23,97],"we":[24],"propose":[25],"new":[27],"adaptive":[28,87],"cascade":[29,38,48],"rule":[30,88,103],"favors":[32],"reliable":[33],"modality":[34,58],"combinations":[35],"through":[36],"classifiers.":[40],"The":[41,85],"order":[42],"the":[44,47,54,68,93,100,111],"classifiers":[45],"in":[46,92,117],"is":[49,73,89,115],"adaptively":[50],"determined":[51],"based":[52],"on":[53],"reliability":[55,62,113],"each":[57],"combination.":[59],"A":[60],"novel":[61],"measure,":[63],"genuinely":[65],"fits":[66],"to":[67,76],"problem,":[72],"also":[74],"proposed":[75,86],"assess":[77],"accept":[78],"or":[79],"reject":[80],"decisions":[81],"classifier.":[84],"more":[90],"robust":[91],"presence":[94],"unreliable":[96],"outperforms":[99],"hard-level":[101],"max":[102],"soft-level":[105],"weighted":[106],"summation":[107],"rule,":[108],"provided":[109],"employed":[112],"measure":[114],"effective":[116],"assessment":[118],"classifier":[120],"decisions.":[121],"Experimental":[122],"results":[123],"support":[125],"this":[126],"assertion":[127],"are":[128],"provided.":[129]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}