{"id":"https://openalex.org/W2099988055","doi":"https://doi.org/10.1109/lsp.2010.2049877","title":"Histogram Equalization-Based Features for Speech, Music, and Song Discrimination","display_name":"Histogram Equalization-Based Features for Speech, Music, and Song Discrimination","publication_year":2010,"publication_date":"2010-05-12","ids":{"openalex":"https://openalex.org/W2099988055","doi":"https://doi.org/10.1109/lsp.2010.2049877","mag":"2099988055"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2010.2049877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2010.2049877","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://oa.upm.es/6969/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065719579","display_name":"Ascensi\u00f3n Gallardo-Antol\u00edn","orcid":"https://orcid.org/0000-0002-9322-3128"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Ascensi\u00f3n Gallardo-Antolin","raw_affiliation_strings":["Department of Signal Theory and Communications, Universidad Carlos III de Madrid, Madrid, Spain","Dept. of Signal Theor. & Commun., Univ. Carlos III de Madrid, Leganes, Spain#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, Universidad Carlos III de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I50357001"]},{"raw_affiliation_string":"Dept. of Signal Theor. & Commun., Univ. Carlos III de Madrid, Leganes, Spain#TAB#","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051480712","display_name":"Juan Manuel Montero","orcid":"https://orcid.org/0000-0002-7908-5400"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan M Montero","raw_affiliation_strings":["Speech Technology Group, Department of Electronic Engineering, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","Dept. of Electron. Eng., Univ. Politec. de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Speech Technology Group, Department of Electronic Engineering, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]},{"raw_affiliation_string":"Dept. of Electron. Eng., Univ. Politec. de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065719579"],"corresponding_institution_ids":["https://openalex.org/I50357001"],"apc_list":null,"apc_paid":null,"fwci":1.3533,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.81362713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"17","issue":"7","first_page":"659","last_page":"662"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8871279954910278},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.805942177772522},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6875728368759155},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6538369655609131},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6334228515625},{"id":"https://openalex.org/keywords/histogram-equalization","display_name":"Histogram equalization","score":0.5999292731285095},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5912702083587646},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5896955728530884},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5480910539627075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5363650918006897},{"id":"https://openalex.org/keywords/equalization","display_name":"Equalization (audio)","score":0.46949270367622375},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4536936581134796},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.41157296299934387},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12838971614837646},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0913955569267273}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8871279954910278},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.805942177772522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6875728368759155},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6538369655609131},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6334228515625},{"id":"https://openalex.org/C136943445","wikidata":"https://www.wikidata.org/wiki/Q1970240","display_name":"Histogram equalization","level":4,"score":0.5999292731285095},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5912702083587646},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5896955728530884},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5480910539627075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5363650918006897},{"id":"https://openalex.org/C75755367","wikidata":"https://www.wikidata.org/wiki/Q104531076","display_name":"Equalization (audio)","level":3,"score":0.46949270367622375},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4536936581134796},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.41157296299934387},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12838971614837646},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0913955569267273},{"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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"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/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/lsp.2010.2049877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2010.2049877","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:oa.upm.es:6969","is_oa":false,"landing_page_url":"https://oa.upm.es/6969/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196323","display_name":"UPM Digital Archive (Technical University of Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I88060688","host_organization_name":"Universidad Polit\u00e9cnica de Madrid","host_organization_lineage":["https://openalex.org/I88060688"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE Signal Processing Letters, ISSN 1070-9908, 2010-05, Vol. 17, No. 7","raw_type":"info:eu-repo/semantics/acceptedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.2777","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.2777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-gth.die.upm.es/research/documentation/AG-087His-10.pdf","raw_type":"text"},{"id":"pmh:oai:dnet:archivodigit::5b66f5bafbd4d039156d805bfd906cb9","is_oa":true,"landing_page_url":"http://oa.upm.es/6969/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Signal Processing Letters, ISSN 1070-9908, 2010-05, Vol. 17, No. 7","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:e-archivo.uc3m.es:10016/32892","is_oa":true,"landing_page_url":"http://hdl.handle.net/10016/32892","pdf_url":null,"source":{"id":"https://openalex.org/S4306400817","display_name":"e-Archivo (Carlos III University of Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I50357001","host_organization_name":"Universidad Carlos III de Madrid","host_organization_lineage":["https://openalex.org/I50357001"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:dnet:archivodigit::5b66f5bafbd4d039156d805bfd906cb9","is_oa":true,"landing_page_url":"http://oa.upm.es/6969/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Signal Processing Letters, ISSN 1070-9908, 2010-05, Vol. 17, No. 7","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.550000011920929},{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313831","display_name":"Comunidad de Madrid","ror":null},{"id":"https://openalex.org/F4320323770","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1986174057","https://openalex.org/W2085457662","https://openalex.org/W2098796164","https://openalex.org/W2106339924","https://openalex.org/W2125540796","https://openalex.org/W2134123343","https://openalex.org/W2141732083","https://openalex.org/W2152175514","https://openalex.org/W2153220212","https://openalex.org/W2169554924","https://openalex.org/W2798455746","https://openalex.org/W4206335616","https://openalex.org/W6678470185"],"related_works":["https://openalex.org/W4377970696","https://openalex.org/W1990594423","https://openalex.org/W2550539038","https://openalex.org/W2164794243","https://openalex.org/W2380849574","https://openalex.org/W2546942002","https://openalex.org/W2767563364","https://openalex.org/W2365115520","https://openalex.org/W2731878113","https://openalex.org/W2408673298"],"abstract_inverted_index":{"In":[0],"this":[1],"letter,":[2],"we":[3],"present":[4],"a":[5,40],"new":[6],"class":[7],"of":[8,71,80],"segment-based":[9,60],"features":[10,50,75],"for":[11],"speech,":[12],"music":[13],"and":[14,39,58,66,73],"song":[15],"discrimination.":[16],"These":[17],"features,":[18],"called":[19],"PHEQ":[20,46,74],"(Polynomial-Fit":[21],"Histogram":[22],"Equalization),":[23],"are":[24],"derived":[25],"from":[26],"the":[27,31,69,78,81],"nonlinear":[28],"relationship":[29],"between":[30],"short-term":[32,49,72],"feature":[33],"distributions":[34],"computed":[35],"at":[36],"segment":[37],"level":[38],"reference":[41],"distribution.":[42],"Results":[43],"show":[44],"that":[45],"characteristics":[47],"outperform":[48],"such":[51,62],"as":[52,63],"Mel":[53],"Frequency":[54],"Cepstrum":[55],"Coefficients":[56],"(MFCC)":[57],"conventional":[59],"ones":[61],"MFCC":[64],"mean":[65],"variance.":[67],"Furthermore,":[68],"combination":[70],"significantly":[76],"improves":[77],"performance":[79],"whole":[82],"system.":[83]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
