{"id":"https://openalex.org/W2402497178","doi":"https://doi.org/10.21437/interspeech.2013-563","title":"Amplitude modulation features for emotion recognition from speech","display_name":"Amplitude modulation features for emotion recognition from speech","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2402497178","doi":"https://doi.org/10.21437/interspeech.2013-563","mag":"2402497178"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-563","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5100737270","display_name":"Md. Jahangir Alam","orcid":"https://orcid.org/0000-0002-3743-9661"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md. Jahangir Alam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023845293","display_name":"Yazid Attabi","orcid":"https://orcid.org/0000-0002-7336-6500"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yazid Attabi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034083532","display_name":"Pierre Dumouchel","orcid":"https://orcid.org/0000-0001-5584-4428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierre Dumouchel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036466893","display_name":"Patrick Kenny","orcid":null},"institutions":[{"id":"https://openalex.org/I9736820","display_name":"\u00c9cole de Technologie Sup\u00e9rieure","ror":"https://ror.org/0020snb74","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I9736820"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Patrick Kenny","raw_affiliation_strings":["Ecole de technologie sup\u00e9rieure"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole de technologie sup\u00e9rieure","institution_ids":["https://openalex.org/I9736820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011489869","display_name":"Douglas O\u2019Shaughnessy","orcid":"https://orcid.org/0000-0002-0110-2346"},"institutions":[{"id":"https://openalex.org/I4210089144","display_name":"Centre National pour la Recherche Scientifique et Technique (CNRST)","ror":"https://ror.org/00675rp98","country_code":"MA","type":"government","lineage":["https://openalex.org/I4210089144"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Douglas O'Shaughnessy","raw_affiliation_strings":["Institut national de la recherche scientifique"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut national de la recherche scientifique","institution_ids":["https://openalex.org/I4210089144"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9325,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87419169,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"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":0.9991999864578247,"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":0.9991999864578247,"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":0.9984999895095825,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"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":0.8628324270248413},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.748759925365448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6610216498374939},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.6569493412971497},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5547552704811096},{"id":"https://openalex.org/keywords/energy-operator","display_name":"Energy operator","score":0.54456627368927},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4839199185371399},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46570688486099243},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.45303308963775635},{"id":"https://openalex.org/keywords/amplitude-modulation","display_name":"Amplitude modulation","score":0.4434422552585602},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4166221022605896},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.38838672637939453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37500572204589844},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3430047035217285},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2825523614883423},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24442201852798462},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.15503010153770447},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10149449110031128},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09062397480010986},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07493597269058228}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8628324270248413},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.748759925365448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6610216498374939},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.6569493412971497},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5547552704811096},{"id":"https://openalex.org/C19579662","wikidata":"https://www.wikidata.org/wiki/Q461145","display_name":"Energy operator","level":3,"score":0.54456627368927},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4839199185371399},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46570688486099243},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.45303308963775635},{"id":"https://openalex.org/C201905106","wikidata":"https://www.wikidata.org/wiki/Q183755","display_name":"Amplitude modulation","level":4,"score":0.4434422552585602},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4166221022605896},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.38838672637939453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37500572204589844},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3430047035217285},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2825523614883423},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24442201852798462},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.15503010153770447},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10149449110031128},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09062397480010986},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07493597269058228},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2013-563","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W68831505","https://openalex.org/W141927798","https://openalex.org/W1501669607","https://openalex.org/W1509874708","https://openalex.org/W1536128259","https://openalex.org/W1538482441","https://openalex.org/W1542841509","https://openalex.org/W1844030040","https://openalex.org/W1976725440","https://openalex.org/W2003837801","https://openalex.org/W2025799736","https://openalex.org/W2032382719","https://openalex.org/W2049633694","https://openalex.org/W2061900096","https://openalex.org/W2063656732","https://openalex.org/W2064641533","https://openalex.org/W2088489891","https://openalex.org/W2090861223","https://openalex.org/W2101426635","https://openalex.org/W2104839346","https://openalex.org/W2137639365","https://openalex.org/W2137997377","https://openalex.org/W2140979961","https://openalex.org/W2148154194","https://openalex.org/W2157000920","https://openalex.org/W2162426832","https://openalex.org/W2462122138","https://openalex.org/W2498787287","https://openalex.org/W3035958916"],"related_works":["https://openalex.org/W2108727544","https://openalex.org/W2548564146","https://openalex.org/W1924444918","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W1559551917","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W1975907141"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,15,25,128,159,190],"speech":[3,40,70,109],"emotion":[4,173],"recognition":[5,157,164],"(SER)":[6],"is":[7,34,87,176],"to":[8,35,77],"identify":[9],"the":[10,26,74,79,84,117,129,156,160,169,179,183,194],"emotional":[11],"or":[12,21],"physical":[13],"state":[14],"a":[16,31,54,108,112,123,187],"human":[17],"being":[18],"from":[19,69,178],"his":[20],"her":[22],"voice.":[23],"One":[24],"most":[27,44],"important":[28],"things":[29],"in":[30],"SER":[32],"task":[33],"extract":[36],"and":[37,82,92,121,140],"select":[38],"relevant":[39],"features":[41,102,151,185],"with":[42],"which":[43],"emotions":[45,68],"could":[46],"be":[47],"recognized.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"present":[53],"smoothed":[55],"nonlinear":[56],"energy":[57,75,86,97],"operator":[58],"(SNEO)-based":[59],"amplitude":[60,91],"modulation":[61],"cepstral":[62,138,148],"coefficients":[63,149],"(AMCC)":[64],"feature":[65],"for":[66,154],"recognizing":[67],"signals.":[71],"SNEO":[72],"estimates":[73],"required":[76],"produce":[78],"AM-FM":[80],"signal,":[81],"then":[83],"estimated":[85],"separated":[88],"into":[89],"its":[90],"frequency":[93],"components":[94],"using":[95,111],"an":[96],"separation":[98],"algorithm":[99],"(ESA).":[100],"AMCC":[101,184],"are":[103,152,166],"obtained":[104],"by":[105],"first":[106],"decomposing":[107],"signal":[110],"C-channel":[113],"gammatone":[114],"filterbank,":[115],"computing":[116],"AM":[118,132],"power":[119,133],"spectrum,":[120],"taking":[122],"discrete":[124],"cosine":[125],"transform":[126],"(DCT)":[127],"root":[130],"compressed":[131],"spectrum.":[134],"Conventional":[135],"MFCC":[136],"(Mel-frequency":[137],"coefficients)":[139],"Mel-warped":[141],"DFT":[142],"(discrete":[143],"Fourier":[144],"transform)":[145],"spectrum":[146],"based":[147],"(MWDCC)":[150],"used":[153],"comparing":[155],"performances":[158],"proposed":[161],"features.":[162],"Emotion":[163],"experiments":[165],"conducted":[167],"on":[168],"FAU":[170],"AIBO":[171],"spontaneous":[172],"corpus.":[174],"It":[175],"observed":[177],"experimental":[180],"results":[181],"that":[182],"provide":[186],"relative":[188],"improvement":[189],"approximately":[191],"3.5%":[192],"over":[193],"baseline":[195],"MFCC.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}