{"id":"https://openalex.org/W2123608681","doi":"https://doi.org/10.1109/icassp.2010.5495020","title":"Dysphonia detection based on modulation spectral features and cepstral coefficients","display_name":"Dysphonia detection based on modulation spectral features and cepstral coefficients","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W2123608681","doi":"https://doi.org/10.1109/icassp.2010.5495020","mag":"2123608681"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","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/A5101734352","display_name":"Maria Markaki","orcid":"https://orcid.org/0000-0001-5779-2078"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Markaki","raw_affiliation_strings":["CSD, Multimedia Informatics Lab, Greece","Multimedia Informatics Lab, CSD, UoC, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSD, Multimedia Informatics Lab, Greece","institution_ids":[]},{"raw_affiliation_string":"Multimedia Informatics Lab, CSD, UoC, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Y. Stylianou","raw_affiliation_strings":["CSD, Multimedia Informatics Lab, Greece","Multimedia Informatics Lab, CSD, UoC, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSD, Multimedia Informatics Lab, Greece","institution_ids":[]},{"raw_affiliation_string":"Multimedia Informatics Lab, CSD, UoC, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044304787","display_name":"Juli\u00e1n D. Arias-Londo\u00f1o","orcid":"https://orcid.org/0000-0002-1928-773X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J.D. Arias-Londono","raw_affiliation_strings":["ICS EUIT de Telecomunicaci\u00f3n, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICS EUIT de Telecomunicaci\u00f3n, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068136205","display_name":"Juan Ignacio Godino-Llorente","orcid":"https://orcid.org/0000-0001-7348-3291"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J.I. Godino-Llorente","raw_affiliation_strings":["ICS EUIT de Telecomunicaci\u00f3n, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICS EUIT de Telecomunicaci\u00f3n, Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0318,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.87642948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"5162","last_page":"5165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","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/T10860","display_name":"Speech and Audio Processing","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7965428233146667},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7223417162895203},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6372609734535217},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6327102184295654},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6285173892974854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6259377002716064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6101597547531128},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5995769500732422},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.4931492209434509},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.4392620027065277},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.43892353773117065},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4312358796596527},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.22901499271392822},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08915001153945923},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08157244324684143}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7965428233146667},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7223417162895203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6372609734535217},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6327102184295654},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6285173892974854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6259377002716064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6101597547531128},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5995769500732422},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.4931492209434509},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.4392620027065277},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.43892353773117065},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4312358796596527},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.22901499271392822},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08915001153945923},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08157244324684143},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2010.5495020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:hispana.mcu.es:17513690","is_oa":false,"landing_page_url":"https://oa.upm.es/7641/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proceedingso f the IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2010 | IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2010 | 14/03/2010 - 19/03/2010 | Dallas, EEUU","raw_type":"info:eu-repo/semantics/acceptedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.663.9786","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.663.9786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://oa.upm.es/7641/2/INVE_MEM_2010_80046.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.705.7273","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.705.7273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csd.uoc.gr/%7Emmarkaki/MMILab-MMarkaki_files/2528_mmarkaki_stylianou_icassp10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W152409035","https://openalex.org/W1544215838","https://openalex.org/W1604938182","https://openalex.org/W2009356821","https://openalex.org/W2013912476","https://openalex.org/W2046678753","https://openalex.org/W2079240096","https://openalex.org/W2103253424","https://openalex.org/W2128280309","https://openalex.org/W2154053567","https://openalex.org/W2157630368","https://openalex.org/W2160641603","https://openalex.org/W2162109146","https://openalex.org/W2170509092","https://openalex.org/W6606288488"],"related_works":["https://openalex.org/W2100203012","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"combine":[4],"modulation":[5,24],"spectral":[6],"features":[7,37],"with":[8,59,65],"mel-frequency":[9],"cepstral":[10],"coefficients":[11],"for":[12],"automatic":[13,75],"detection":[14],"of":[15,21],"dysphonia.":[16],"For":[17],"classification":[18],"purposes,":[19],"dimensions":[20],"the":[22,85,91],"original":[23],"spectra":[25],"are":[26,38,62],"reduced":[27],"using":[28,79],"higher":[29],"order":[30],"singular":[31],"value":[32],"decomposition":[33],"(HOSVD).":[34],"Most":[35],"relevant":[36],"selected":[39],"based":[40],"on":[41],"their":[42],"mutual":[43],"information":[44,89],"to":[45,72,90],"discrimination":[46],"between":[47],"normophonic":[48],"and":[49],"dysphonic":[50],"speakers":[51],"made":[52],"by":[53],"experts.":[54],"Features":[55],"that":[56,84],"highly":[57],"correlate":[58],"voice":[60],"alterations":[61],"associated":[63],"then":[64],"a":[66],"support":[67],"vector":[68],"machine":[69],"(SVM)":[70],"classifier":[71],"provide":[73],"an":[74],"decision.":[76],"Recognition":[77],"experiments":[78],"two":[80],"different":[81],"databases":[82],"suggest":[83],"system":[86],"provides":[87],"complementary":[88],"standard":[92],"mel-cepstral":[93],"features.":[94]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}