{"id":"https://openalex.org/W2102637672","doi":"https://doi.org/10.1109/icme.2009.5202524","title":"Audio-based classification of speaker characteristics","display_name":"Audio-based classification of speaker characteristics","publication_year":2009,"publication_date":"2009-06-01","ids":{"openalex":"https://openalex.org/W2102637672","doi":"https://doi.org/10.1109/icme.2009.5202524","mag":"2102637672"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2009.5202524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2009.5202524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Multimedia and Expo","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/A5067746058","display_name":"Promiti Dutta","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Promiti Dutta","raw_affiliation_strings":["Columbia University, New York, NY, USA","Columbia University, New York., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York., USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040143997","display_name":"Alexander Haubold","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Haubold","raw_affiliation_strings":["Columbia University, New York, NY, USA","Columbia University, New York., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York., USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.13066298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"422","last_page":"425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9890000224113464,"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":0.9848999977111816,"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":0.7680233716964722},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6930115818977356},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.627120852470398},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6211917400360107},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5251983404159546},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5110069513320923},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4428026080131531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4414999186992645},{"id":"https://openalex.org/keywords/demographics","display_name":"Demographics","score":0.44095492362976074},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43752729892730713},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43484562635421753},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.43135330080986023},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.38159286975860596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7680233716964722},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6930115818977356},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.627120852470398},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6211917400360107},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5251983404159546},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5110069513320923},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4428026080131531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4414999186992645},{"id":"https://openalex.org/C2780084366","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demographics","level":2,"score":0.44095492362976074},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43752729892730713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43484562635421753},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.43135330080986023},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38159286975860596},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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/icme.2009.5202524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2009.5202524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.363.2899","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.363.2899","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aquaphoenix.com/publication/icme2009_audioclass.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1570448133","https://openalex.org/W2015412875","https://openalex.org/W2034243835","https://openalex.org/W2127533594","https://openalex.org/W2132247852","https://openalex.org/W2137537225","https://openalex.org/W2171968615","https://openalex.org/W2966207845","https://openalex.org/W6685441411"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W4401661962","https://openalex.org/W4247736853","https://openalex.org/W1521049138","https://openalex.org/W2997340161","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"The":[0],"human":[1],"voice":[2],"is":[3],"primarily":[4],"a":[5,17,131],"carrier":[6],"of":[7,21,46,56,93,97,110,148],"speech,":[8],"but":[9],"it":[10],"also":[11],"contains":[12],"non-linguistic":[13],"features":[14,52,61,71,78,129,143],"unique":[15,102],"to":[16,86,118],"speaker":[18,23,57,103,149],"and":[19,37,50,65,75,130,141],"indicative":[20],"various":[22,47],"demographics,":[24],"e.g.":[25],"gender,":[26],"nativity,":[27],"ethnicity.":[28],"Such":[29],"characteristics":[30],"are":[31,79,144],"helpful":[32],"cues":[33],"for":[34,53,106,124,146],"audio/video":[35],"search":[36],"retrieval.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"evaluate":[43],"the":[44],"effects":[45],"low-,":[48],"mid-,":[49],"high-level":[51,76,142],"effective":[54],"classification":[55,126],"characteristics.":[58,150],"Low-level":[59],"signal-based":[60],"include":[62],"MFCCs,":[63],"LPCs,":[64],"six":[66],"spectral":[67],"features;":[68,74],"mid-level":[69,87,128],"statistical":[70],"model":[72],"low-level":[73],"semantic":[77],"based":[80],"on":[81,120],"selected":[82],"phonemes":[83],"in":[84,114],"addition":[85],"features.":[88],"Our":[89],"data":[90,123],"set":[91],"consists":[92],"approximately":[94],"76.4":[95],"hours":[96],"annotated":[98],"audio":[99],"with":[100],"2786":[101],"segments":[104],"used":[105],"classification.":[107],"Quantitative":[108],"evaluation":[109],"our":[111,121],"method":[112],"results":[113],"accuracy":[115],"rates":[116],"up":[117],"98.6%":[119],"test":[122],"male/female":[125],"using":[127],"linear":[132],"kernel":[133],"support":[134],"vector":[135],"machine.":[136],"We":[137],"determine":[138],"that":[139],"mid-":[140],"optimal":[145],"identification":[147]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}