{"id":"https://openalex.org/W184047294","doi":"https://doi.org/10.21437/eurospeech.2003-177","title":"Speaker recognition using MPEG-7 descriptors","display_name":"Speaker recognition using MPEG-7 descriptors","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W184047294","doi":"https://doi.org/10.21437/eurospeech.2003-177","mag":"184047294"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-177","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5026378467","display_name":"Hyoung\u2010Gook Kim","orcid":"https://orcid.org/0000-0002-1518-4100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyoung-Gook Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002962238","display_name":"Edgar Berdahl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edgar Berdahl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039275567","display_name":"Nicolas Moreau","orcid":"https://orcid.org/0000-0002-5779-5778"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Moreau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113970295","display_name":"Thomas Sikora","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Sikora","raw_affiliation_strings":["Technical University of Berlin,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Berlin,","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2252,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.8731099,"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":"489","last_page":"492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9998000264167786,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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":0.9918000102043152,"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":0.7708015441894531},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.7429660558700562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7239112257957458},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7155718803405762},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.68742835521698},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6755430698394775},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6266167163848877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6247380971908569},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5313124656677246},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49788570404052734},{"id":"https://openalex.org/keywords/independent-component-analysis","display_name":"Independent component analysis","score":0.45005014538764954},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10201841592788696}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7708015441894531},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.7429660558700562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7239112257957458},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7155718803405762},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.68742835521698},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6755430698394775},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6266167163848877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6247380971908569},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5313124656677246},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49788570404052734},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.45005014538764954},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10201841592788696},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"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:10.21437/eurospeech.2003-177","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.232","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.nue.tu-berlin.de/publications/papers/EuSp03-539.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W124356247","https://openalex.org/W2099741732","https://openalex.org/W2123649031","https://openalex.org/W2148694408"],"related_works":["https://openalex.org/W2121429698","https://openalex.org/W2182042810","https://openalex.org/W4252230435","https://openalex.org/W55679925","https://openalex.org/W3080404860","https://openalex.org/W2046761971","https://openalex.org/W3144722888","https://openalex.org/W2089650474","https://openalex.org/W2364896863","https://openalex.org/W1560125148"],"abstract_inverted_index":{"Our":[0],"purpose":[1],"is":[2,31,84],"to":[3,47],"evaluate":[4],"the":[5,87],"efficiency":[6],"of":[7,63],"MPEG-7":[8,16,43,60],"audio":[9,19],"descriptors":[10,44,61],"for":[11,25,52,93],"speaker":[12,33,88,110],"recognition.":[13],"The":[14,55],"upcoming":[15],"standard":[17],"provides":[18],"feature":[20,56,95],"descriptors,":[21],"which":[22,37],"are":[23,45,91],"useful":[24],"many":[26],"applications.":[27],"One":[28],"example":[29],"application":[30],"a":[32,109],"recognition":[34,89,111],"system,":[35],"in":[36,108],"reduced-dimension":[38],"log-spectral":[39],"features":[40],"based":[41,58],"on":[42,59],"used":[46],"train":[48],"hidden":[49],"Markov":[50],"models":[51],"individual":[53],"speakers.":[54],"extraction":[57,96],"consists":[62],"three":[64],"main":[65],"stages:":[66],"Normalized":[67],"Audio":[68],"Spectrum":[69],"Envelope":[70],"(NASE),":[71],"Principal":[72],"Component":[73,78],"Analysis":[74,79],"(PCA)":[75],"and":[76,106],"Independent":[77],"(ICA).":[80],"An":[81],"experimental":[82],"study":[83],"presented":[85],"where":[86],"rates":[90],"compared":[92],"different":[94],"methods.":[97],"Using":[98],"ICA,":[99],"we":[100],"achieved":[101],"better":[102],"results":[103],"than":[104],"NASE":[105],"PCA":[107],"system.":[112]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}