{"id":"https://openalex.org/W2136873765","doi":"https://doi.org/10.1186/1687-4722-2012-16","title":"Perceptual audio features for emotion detection","display_name":"Perceptual audio features for emotion detection","publication_year":2012,"publication_date":"2012-05-04","ids":{"openalex":"https://openalex.org/W2136873765","doi":"https://doi.org/10.1186/1687-4722-2012-16","mag":"2136873765"},"language":"en","primary_location":{"id":"doi:10.1186/1687-4722-2012-16","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-16","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/1687-4722-2012-16","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/1687-4722-2012-16","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010304193","display_name":"Mehmet Sezgin","orcid":"https://orcid.org/0000-0002-7921-564X"},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mehmet Cenk Sezgin","raw_affiliation_strings":["Multimedia Signal Processing and Pattern Recognition Lab., Department of Electronics and Communications, Istanbul Technical University, Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Signal Processing and Pattern Recognition Lab., Department of Electronics and Communications, Istanbul Technical University, Istanbul, Turkey","institution_ids":["https://openalex.org/I48912391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089754740","display_name":"Bilge G\u00fcnsel","orcid":"https://orcid.org/0000-0003-3628-3316"},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Bilge Gunsel","raw_affiliation_strings":["Multimedia Signal Processing and Pattern Recognition Lab., Department of Electronics and Communications, Istanbul Technical University, Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Signal Processing and Pattern Recognition Lab., Department of Electronics and Communications, Istanbul Technical University, Istanbul, Turkey","institution_ids":["https://openalex.org/I48912391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022600471","display_name":"G\u00fcne\u015f Karabulut Kurt","orcid":"https://orcid.org/0000-0001-7188-2619"},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Gunes Karabulut Kurt","raw_affiliation_strings":["Multimedia Signal Processing and Pattern Recognition Lab., Department of Electronics and Communications, Istanbul Technical University, Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Signal Processing and Pattern Recognition Lab., Department of Electronics and Communications, Istanbul Technical University, Istanbul, Turkey","institution_ids":["https://openalex.org/I48912391"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":3.4676,"has_fulltext":true,"cited_by_count":77,"citation_normalized_percentile":{"value":0.94725858,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2012","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9961000084877014,"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/speech-recognition","display_name":"Speech recognition","score":0.7350066900253296},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.692922055721283},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6266562342643738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6052648425102234},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.49057120084762573},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.48147884011268616},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.4363335371017456},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.42485353350639343},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4023210406303406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3892277479171753},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.27076035737991333},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09816578030586243}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7350066900253296},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.692922055721283},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6266562342643738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6052648425102234},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.49057120084762573},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48147884011268616},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.4363335371017456},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.42485353350639343},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4023210406303406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3892277479171753},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27076035737991333},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09816578030586243},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/1687-4722-2012-16","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-16","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/1687-4722-2012-16","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:polen.itu.edu.tr:11527/38957","is_oa":false,"landing_page_url":"https://hdl.handle.net/11527/38957","pdf_url":null,"source":{"id":"https://openalex.org/S4306400460","display_name":"Istanbul Technical University Academic Open Archive (Istanbul Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I48912391","host_organization_name":"Istanbul Technical University","host_organization_lineage":["https://openalex.org/I48912391"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:publications.polymtl.ca:48310","is_oa":false,"landing_page_url":"https://publications.polymtl.ca/48310/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article de revue"}],"best_oa_location":{"id":"doi:10.1186/1687-4722-2012-16","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-16","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/1687-4722-2012-16","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2136873765.pdf","grobid_xml":"https://content.openalex.org/works/W2136873765.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1570448133","https://openalex.org/W1589520724","https://openalex.org/W1606487971","https://openalex.org/W1815942593","https://openalex.org/W1966797434","https://openalex.org/W1970385421","https://openalex.org/W2032254851","https://openalex.org/W2068680500","https://openalex.org/W2074788634","https://openalex.org/W2078833921","https://openalex.org/W2092489135","https://openalex.org/W2097732741","https://openalex.org/W2099767163","https://openalex.org/W2102298245","https://openalex.org/W2102953093","https://openalex.org/W2104862701","https://openalex.org/W2111926505","https://openalex.org/W2117979998","https://openalex.org/W2123504579","https://openalex.org/W2123861288","https://openalex.org/W2125462608","https://openalex.org/W2137639365","https://openalex.org/W2149628368","https://openalex.org/W2153635508","https://openalex.org/W2158061940","https://openalex.org/W2167854178","https://openalex.org/W2169166781","https://openalex.org/W2466512847","https://openalex.org/W2966207845","https://openalex.org/W4250499635","https://openalex.org/W6611528966"],"related_works":["https://openalex.org/W1970025505","https://openalex.org/W2030358499","https://openalex.org/W1966585405","https://openalex.org/W2093863013","https://openalex.org/W2046078639","https://openalex.org/W2493561494","https://openalex.org/W2069086801","https://openalex.org/W2026861386","https://openalex.org/W4288315282","https://openalex.org/W2951122819"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"this":[2],"article,":[3],"we":[4,53],"propose":[5],"a":[6],"new":[7],"set":[8],"of":[9,33,49,85,94,96,100,102,109],"acoustic":[10],"features":[11,19,56,71],"for":[12,67,165,171],"automatic":[13],"emotion":[14,68,158],"recognition":[15,159],"from":[16,42],"audio.":[17],"The":[18,70],"are":[20,28,161],"based":[21,76],"on":[22,57,77],"the":[23,43,50,58,78,82,86,103,106,122,130,135,157],"perceptual":[24,31,60,113],"quality":[25,35],"metrics":[26],"that":[27,120,156],"given":[29],"in":[30,73,169],"evaluation":[32],"audio":[34],"known":[36],"as":[37],"ITU":[38],"BS.1387":[39],"recommendation.":[40],"Starting":[41],"outer":[44],"and":[45,112,142,149,167,173],"middle":[46],"ear":[47],"models":[48],"auditory":[51],"system,":[52],"base":[54],"our":[55],"masked":[59],"loudness":[61,84],"which":[62],"defines":[63],"relatively":[64],"objective":[65],"criteria":[66],"detection.":[69],"computed":[72],"critical":[74],"bands":[75],"reference":[79],"concept":[80],"include":[81],"partial":[83],"emotional":[87,89,104,110],"difference,":[88,105],"difference-to-perceptual":[90],"mask":[91],"ratio,":[92],"measures":[93,99],"alterations":[95],"temporal":[97],"envelopes,":[98],"harmonics":[101],"occurrence":[107],"probability":[108],"blocks,":[111],"bandwidth.":[114],"A":[115],"soft-majority":[116],"voting":[117,125],"decision":[118],"rule":[119],"strengthens":[121],"conventional":[123],"majority":[124],"is":[126,154],"proposed":[127],"to":[128,134],"assess":[129],"classifier":[131],"outputs.":[132],"Compared":[133],"state-of-the-art":[136],"systems":[137],"including":[138],"Munich":[139],"Open-Source":[140],"Emotion":[141],"Affect":[143],"Recognition":[144],"Toolkit,":[145,148],"Hidden":[146],"Markov":[147],"Generalized":[150],"Discriminant":[151],"Analysis,":[152],"it":[153],"shown":[155],"rates":[160],"improved":[162],"between":[163],"7-16%":[164],"EMO-DB":[166],"7-11%":[168],"VAM":[170],"\"all\"":[172],"\"valence\"":[174],"tasks.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
