{"id":"https://openalex.org/W3014215778","doi":"https://doi.org/10.1109/tencon50793.2020.9293852","title":"On The Differences Between Song and Speech Emotion Recognition: Effect of Feature Sets, Feature Types, and Classifiers","display_name":"On The Differences Between Song and Speech Emotion Recognition: Effect of Feature Sets, Feature Types, and Classifiers","publication_year":2020,"publication_date":"2020-11-16","ids":{"openalex":"https://openalex.org/W3014215778","doi":"https://doi.org/10.1109/tencon50793.2020.9293852","mag":"3014215778"},"language":"en","primary_location":{"id":"doi:10.1109/tencon50793.2020.9293852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon50793.2020.9293852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.00200","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065879041","display_name":"Bagus Tris Atmaja","orcid":"https://orcid.org/0000-0003-1560-2824"},"institutions":[{"id":"https://openalex.org/I166843116","display_name":"Sepuluh Nopember Institute of Technology","ror":"https://ror.org/05kbmmt89","country_code":"ID","type":"education","lineage":["https://openalex.org/I166843116"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Bagus Tris Atmaja","raw_affiliation_strings":["Department of Engineering Physics, Sepuluh Nopember Institute of Technology, Surabaya, Indonesia","sepuluh nopember institute of technology"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Physics, Sepuluh Nopember Institute of Technology, Surabaya, Indonesia","institution_ids":["https://openalex.org/I166843116"]},{"raw_affiliation_string":"sepuluh nopember institute of technology","institution_ids":["https://openalex.org/I166843116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":["School of Information Science, Japan Adv. Inst. of Sci. & Tech., Nomi, Japan","Japan Advanced Institute of Science and Technology,School of Information Science,Nomi,Japan"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Adv. Inst. of Sci. & Tech., Nomi, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,School of Information Science,Nomi,Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065879041"],"corresponding_institution_ids":["https://openalex.org/I166843116"],"apc_list":null,"apc_paid":null,"fwci":0.4585,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59608611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"968","last_page":"972"},"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":0.9991000294685364,"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":0.9955000281333923,"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/feature","display_name":"Feature (linguistics)","score":0.7310647368431091},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6289441585540771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.600906491279602},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5781116485595703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.552519679069519},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5363949537277222},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.5025155544281006},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5002284049987793},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.461215615272522},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4185924530029297},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34936583042144775},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0718311071395874},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05290648341178894}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7310647368431091},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6289441585540771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.600906491279602},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5781116485595703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.552519679069519},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5363949537277222},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.5025155544281006},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5002284049987793},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.461215615272522},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4185924530029297},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34936583042144775},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0718311071395874},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05290648341178894},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems 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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tencon50793.2020.9293852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon50793.2020.9293852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.00200","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.00200","pdf_url":"https://arxiv.org/pdf/2004.00200","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:irdb.nii.ac.jp:01333:0004847698","is_oa":true,"landing_page_url":"http://hdl.handle.net/10119/17070","pdf_url":"https://dspace.jaist.ac.jp/dspace/bitstream/10119/17070/1/3365.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","raw_type":"conference paper"},{"id":"mag:3014215778","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2004.00200.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2004.00200","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.00200","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.00200","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.00200","pdf_url":"https://arxiv.org/pdf/2004.00200","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1573035800","https://openalex.org/W2088312083","https://openalex.org/W2090777335","https://openalex.org/W2192412620","https://openalex.org/W2239141610","https://openalex.org/W2625297138","https://openalex.org/W3010325101","https://openalex.org/W3016092640","https://openalex.org/W3028108576","https://openalex.org/W3081192838","https://openalex.org/W6748326514","https://openalex.org/W6782183663","https://openalex.org/W7027646976"],"related_works":["https://openalex.org/W2305902301","https://openalex.org/W2347663474","https://openalex.org/W2107500058","https://openalex.org/W3018062911","https://openalex.org/W2346704485","https://openalex.org/W2077498515","https://openalex.org/W2210331589","https://openalex.org/W2221113436","https://openalex.org/W2251219786","https://openalex.org/W3088783238","https://openalex.org/W3037334811","https://openalex.org/W2787391987","https://openalex.org/W3147489381","https://openalex.org/W3034417893","https://openalex.org/W3105296980","https://openalex.org/W2547127820","https://openalex.org/W2739515809","https://openalex.org/W2883085","https://openalex.org/W2159543062","https://openalex.org/W2900781839"],"abstract_inverted_index":{"In":[0,97],"this":[1,112],"paper,":[2],"we":[3],"argue":[4],"that":[5,90],"singing":[6],"voice":[7],"(song)":[8],"is":[9,92],"more":[10,93],"emotional":[11,94],"than":[12,95,108],"speech.":[13,96],"We":[14],"evaluate":[15],"different":[16],"features":[17,104],"sets,":[18],"feature":[19,31,38],"types,":[20,39],"and":[21,26,35,42,46,53,77],"classifiers":[22],"on":[23,59,80,121],"both":[24,60],"song":[25,76,91],"speech":[27,62,78],"emotion":[28],"recognition.":[29],"Three":[30],"sets:":[32],"GeMAPS,":[33],"pyAudioAnalysis,":[34],"LibROSA;":[36],"two":[37,87],"low-level":[40,109],"descriptors":[41,110],"high-level":[43,99,131],"statistical":[44,100],"functions;":[45],"four":[47],"classifiers:":[48],"multilayer":[49],"perceptron,":[50],"LSTM,":[51],"GRU,":[52],"convolution":[54],"neural":[55],"networks;":[56],"are":[57],"examined":[58],"songand":[61],"data":[63,79],"with":[64],"the":[65,82,118,122,127],"same":[66,83],"parameter":[67],"values.":[68],"The":[69],"results":[70,88],"show":[71],"no":[72],"remarkable":[73],"difference":[74],"between":[75],"using":[81],"method.":[84],"Comparisons":[85],"of":[86,102,130],"reveal":[89],"addition,":[98],"functions":[101],"acoustic":[103],"gained":[105],"higher":[106],"performance":[107],"in":[111],"classification":[113],"task.":[114],"This":[115],"result":[116],"strengthens":[117],"previous":[119],"finding":[120],"regression":[123],"task":[124],"which":[125],"reported":[126],"advantage":[128],"use":[129],"features.":[132]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}