{"id":"https://openalex.org/W2883496341","doi":"https://doi.org/10.1109/taffc.2018.2858255","title":"Feature Pooling of Modulation Spectrum Features for Improved Speech Emotion Recognition in the Wild","display_name":"Feature Pooling of Modulation Spectrum Features for Improved Speech Emotion Recognition in the Wild","publication_year":2018,"publication_date":"2018-07-23","ids":{"openalex":"https://openalex.org/W2883496341","doi":"https://doi.org/10.1109/taffc.2018.2858255","mag":"2883496341"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2018.2858255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2018.2858255","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Transactions on Affective Computing","raw_type":"journal-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/A5009407218","display_name":"Anderson R. Avila","orcid":"https://orcid.org/0000-0002-3088-5116"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Anderson R. Avila","raw_affiliation_strings":["Telecommunications, INRS-EMT, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Telecommunications, INRS-EMT, Montreal, QC, Canada","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056705041","display_name":"Zahid Akhtar","orcid":"https://orcid.org/0000-0002-5026-5416"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zahid Akhtar","raw_affiliation_strings":["Telecommunications, INRS-EMT, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Telecommunications, INRS-EMT, Montreal, QC, Canada","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068457267","display_name":"Jo\u00e3o Felipe Santos","orcid":"https://orcid.org/0000-0003-3934-3943"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Joao F. Santos","raw_affiliation_strings":["Telecommunications, INRS-EMT, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Telecommunications, INRS-EMT, Montreal, QC, Canada","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011489869","display_name":"Douglas O\u2019Shaughnessy","orcid":"https://orcid.org/0000-0002-0110-2346"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Douglas OShaughnessy","raw_affiliation_strings":["Telecommunications, INRS-EMT, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Telecommunications, INRS-EMT, Montreal, QC, Canada","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065418889","display_name":"Tiago H. Falk","orcid":"https://orcid.org/0000-0002-5739-2514"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tiago H. Falk","raw_affiliation_strings":["Telecommunications, INRS-EMT, Montreal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Telecommunications, INRS-EMT, Montreal, QC, Canada","institution_ids":["https://openalex.org/I39481719"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009407218"],"corresponding_institution_ids":["https://openalex.org/I39481719"],"apc_list":null,"apc_paid":null,"fwci":2.8681,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.90679336,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"12","issue":"1","first_page":"177","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9970999956130981,"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/reverberation","display_name":"Reverberation","score":0.7782807350158691},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7032458782196045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6915408968925476},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6231717467308044},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5921972990036011},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.587971031665802},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5073408484458923},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49022990465164185},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.4760662913322449},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4333837330341339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42409706115722656},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41405826807022095},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10017642378807068},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08270889520645142}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7782807350158691},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7032458782196045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6915408968925476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6231717467308044},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5921972990036011},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.587971031665802},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5073408484458923},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49022990465164185},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.4760662913322449},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4333837330341339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42409706115722656},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41405826807022095},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10017642378807068},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08270889520645142},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2018.2858255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2018.2858255","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Transactions on Affective Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W396690109","https://openalex.org/W1480583224","https://openalex.org/W1501669607","https://openalex.org/W1587906680","https://openalex.org/W1810943226","https://openalex.org/W1815076433","https://openalex.org/W1904365287","https://openalex.org/W1966359074","https://openalex.org/W1983108229","https://openalex.org/W1987759408","https://openalex.org/W2002016471","https://openalex.org/W2018543616","https://openalex.org/W2028819669","https://openalex.org/W2045528981","https://openalex.org/W2064641533","https://openalex.org/W2074788634","https://openalex.org/W2090777335","https://openalex.org/W2094866499","https://openalex.org/W2095705004","https://openalex.org/W2102298245","https://openalex.org/W2105854852","https://openalex.org/W2107460374","https://openalex.org/W2118479009","https://openalex.org/W2123737232","https://openalex.org/W2125734472","https://openalex.org/W2127707623","https://openalex.org/W2134554540","https://openalex.org/W2136682440","https://openalex.org/W2137639365","https://openalex.org/W2151484683","https://openalex.org/W2153822685","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2243226955","https://openalex.org/W2313339984","https://openalex.org/W2318465276","https://openalex.org/W2346454595","https://openalex.org/W2506282302","https://openalex.org/W2511508976","https://openalex.org/W2525246137","https://openalex.org/W2534419903","https://openalex.org/W2751214333","https://openalex.org/W2760256423","https://openalex.org/W2919115771","https://openalex.org/W4232282348","https://openalex.org/W6613520308","https://openalex.org/W6638273328","https://openalex.org/W6638545294","https://openalex.org/W6640036494","https://openalex.org/W6674330103","https://openalex.org/W6678557583","https://openalex.org/W6684191040","https://openalex.org/W6744999298"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W2770624987","https://openalex.org/W4256175191","https://openalex.org/W3023111453","https://openalex.org/W2786830879","https://openalex.org/W4310841718","https://openalex.org/W560265342"],"abstract_inverted_index":{"Interest":[0],"in":[1,6,13,35],"affective":[2,15],"computing":[3],"is":[4,113],"burgeoning,":[5],"great":[7],"part":[8],"due":[9],"to":[10,115],"its":[11],"role":[12],"emerging":[14],"human-computer":[16],"interfaces":[17],"(HCI).":[18],"To":[19],"date,":[20],"the":[21,39,85,89,97,137,144,154,166,170,173],"majority":[22],"of":[23,41,124,136,140,172],"existing":[24],"research":[25],"on":[26,32,44,63,92,132],"automated":[27],"emotion":[28,57,93],"analysis":[29],"has":[30,91],"relied":[31],"data":[33],"collected":[34],"controlled":[36],"environments.":[37],"With":[38],"rise":[40],"HCI":[42],"applications":[43],"mobile":[45],"devices,":[46],"however,":[47],"so-called":[48],"\u201cin-the-wild\u201d":[49],"settings":[50],"have":[51],"posed":[52],"a":[53,106,117],"serious":[54],"threat":[55],"for":[56,121,176],"recognition":[58,94],"systems,":[59],"particularly":[60],"those":[61],"based":[62],"voice.":[64],"In":[65,80],"this":[66,81],"case,":[67],"environmental":[68],"factors":[69],"such":[70],"as":[71],"ambient":[72],"noise":[73],"and":[74,95,127,160],"reverberation":[75],"severely":[76],"hamper":[77],"system":[78,120],"performance.":[79],"paper,":[82],"we":[83,104],"quantify":[84],"detrimental":[86],"effects":[87],"that":[88,112],"environment":[90],"explore":[96],"benefits":[98,171],"achievable":[99],"with":[100,150,165],"speech":[101,151],"enhancement.":[102],"Moreover,":[103],"propose":[105],"modulation":[107],"spectral":[108],"feature":[109,146],"pooling":[110,147],"scheme":[111],"shown":[114],"outperform":[116],"state-of-the-art":[118],"benchmark":[119,155],"environment-robust":[122],"prediction":[123],"spontaneous":[125,141],"arousal":[126],"valence":[128],"emotional":[129],"primitives.":[130],"Experiments":[131],"an":[133],"environment-corrupted":[134],"version":[135],"RECOLA":[138],"dataset":[139],"interactions":[142],"show":[143,169],"proposed":[145,174],"scheme,":[148],"combined":[149],"enhancement,":[152],"outperforming":[153],"across":[156],"different":[157],"noise-only,":[158],"reverberation-only":[159],"noise-plus-reverberation":[161],"conditions.":[162],"Additional":[163],"tests":[164],"SEWA":[167],"database":[168],"method":[175],"in-the-wild":[177],"applications.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}