{"id":"https://openalex.org/W4383219119","doi":"https://doi.org/10.1109/dsp58604.2023.10167766","title":"Italian Speech Emotion Recognition","display_name":"Italian Speech Emotion Recognition","publication_year":2023,"publication_date":"2023-06-11","ids":{"openalex":"https://openalex.org/W4383219119","doi":"https://doi.org/10.1109/dsp58604.2023.10167766"},"language":"en","primary_location":{"id":"doi:10.1109/dsp58604.2023.10167766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsp58604.2023.10167766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 24th International Conference on Digital Signal Processing (DSP)","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/A5020915296","display_name":"Irene Mantegazza","orcid":null},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Irene Mantegazza","raw_affiliation_strings":["University of Milan,Department of Computer Science","Department of Computer Science, University of Milan"],"affiliations":[{"raw_affiliation_string":"University of Milan,Department of Computer Science","institution_ids":["https://openalex.org/I189158943"]},{"raw_affiliation_string":"Department of Computer Science, University of Milan","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013285272","display_name":"Stavros Ntalampiras","orcid":"https://orcid.org/0000-0003-3482-9215"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stavros Ntalampiras","raw_affiliation_strings":["University of Milan,Department of Computer Science","Department of Computer Science, University of Milan"],"affiliations":[{"raw_affiliation_string":"University of Milan,Department of Computer Science","institution_ids":["https://openalex.org/I189158943"]},{"raw_affiliation_string":"Department of Computer Science, University of Milan","institution_ids":["https://openalex.org/I189158943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020915296"],"corresponding_institution_ids":["https://openalex.org/I189158943"],"apc_list":null,"apc_paid":null,"fwci":1.42,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82155599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9980999827384949,"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":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/disgust","display_name":"Disgust","score":0.8132928609848022},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7240777611732483},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6467602849006653},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6373625993728638},{"id":"https://openalex.org/keywords/surprise","display_name":"Surprise","score":0.5887055397033691},{"id":"https://openalex.org/keywords/sadness","display_name":"Sadness","score":0.5755383968353271},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.5719326138496399},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5267348289489746},{"id":"https://openalex.org/keywords/anger","display_name":"Anger","score":0.5140730142593384},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4932376742362976},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4679775536060333},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3863699734210968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38023698329925537},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3503261208534241},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15337201952934265}],"concepts":[{"id":"https://openalex.org/C2777375102","wikidata":"https://www.wikidata.org/wiki/Q208351","display_name":"Disgust","level":3,"score":0.8132928609848022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7240777611732483},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6467602849006653},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6373625993728638},{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.5887055397033691},{"id":"https://openalex.org/C2779812673","wikidata":"https://www.wikidata.org/wiki/Q169251","display_name":"Sadness","level":3,"score":0.5755383968353271},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.5719326138496399},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5267348289489746},{"id":"https://openalex.org/C2779302386","wikidata":"https://www.wikidata.org/wiki/Q79871","display_name":"Anger","level":2,"score":0.5140730142593384},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4932376742362976},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4679775536060333},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3863699734210968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38023698329925537},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3503261208534241},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15337201952934265},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsp58604.2023.10167766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsp58604.2023.10167766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 24th International Conference on Digital Signal Processing (DSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W589698015","https://openalex.org/W1492815834","https://openalex.org/W2003948868","https://openalex.org/W2074788634","https://openalex.org/W2509065397","https://openalex.org/W2931364255","https://openalex.org/W2939574508","https://openalex.org/W2955544543","https://openalex.org/W3005153176","https://openalex.org/W3098357269","https://openalex.org/W3123679857","https://openalex.org/W3151965712","https://openalex.org/W3161714660","https://openalex.org/W3208480086","https://openalex.org/W4225315675","https://openalex.org/W4232132981","https://openalex.org/W4313162486","https://openalex.org/W4323240341","https://openalex.org/W4323519394","https://openalex.org/W4324116353","https://openalex.org/W4327785480","https://openalex.org/W6617505242","https://openalex.org/W6801326556"],"related_works":["https://openalex.org/W4238520549","https://openalex.org/W3216173459","https://openalex.org/W2794357331","https://openalex.org/W4242611441","https://openalex.org/W4242034606","https://openalex.org/W2037174948","https://openalex.org/W4388134110","https://openalex.org/W3199829813","https://openalex.org/W2400641934","https://openalex.org/W2018346846"],"abstract_inverted_index":{"Affective":[0],"computing":[1],"is":[2,54],"gaining":[3],"increased":[4],"interest":[5],"by":[6],"the":[7,11,15,34,57,70,116,124],"scientific":[8],"community":[9],"in":[10,69],"last":[12],"decades":[13],"with":[14,99],"acoustic":[16],"modality":[17],"playing":[18],"a":[19,41,47,100],"central":[20],"role.":[21],"This":[22],"paper":[23],"presents":[24],"an":[25],"extensive":[26],"computational":[27],"analysis":[28],"of":[29,75,115],"emotional":[30,77],"speech":[31],"focusing":[32],"on":[33,46],"Italian":[35,76],"language.":[36],"More":[37],"precisely,":[38],"we":[39,84],"propose":[40],"novel":[42],"classification":[43],"algorithm":[44],"based":[45],"suitable":[48,101],"data":[49],"augmentation":[50],"scheme.":[51],"The":[52,111],"aim":[53],"to":[55],"classify":[56],"seven":[58],"emotions":[59],"(anger,":[60],"disgust,":[61],"fear,":[62],"joy,":[63],"neutral,":[64],"sadness,":[65],"and":[66,93,106,113],"surprise)":[67],"included":[68],"only":[71],"publicly":[72],"available":[73],"database":[74],"speech,":[78],"i.e.":[79,103],"EMOVO.":[80],"To":[81],"this":[82],"end,":[83],"employed":[85],"two":[86],"feature":[87],"sets,":[88],"Mel":[89],"Frequency":[90],"Cepstral":[91],"Coefficients":[92],"log-Mel":[94],"spectrogram,":[95],"each":[96],"one":[97],"combined":[98],"classifier,":[102],"Mutilayer":[104],"perceptron":[105],"Convolutional":[107],"neural":[108],"network":[109],"respectively.":[110],"implementation":[112],"evaluation":[114],"proposed":[117],"SER":[118],"pipeline":[119],"can":[120],"be":[121],"accessed":[122],"through":[123],"following":[125],"link:":[126],"https://github.com/irenemante/ser_emovo":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}