{"id":"https://openalex.org/W4405488951","doi":"https://doi.org/10.1109/embc53108.2024.10782952","title":"Emotion Recognition from Speech Signals by Mel-Spectrogram and a CNN-RNN","display_name":"Emotion Recognition from Speech Signals by Mel-Spectrogram and a CNN-RNN","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4405488951","doi":"https://doi.org/10.1109/embc53108.2024.10782952","pmid":"https://pubmed.ncbi.nlm.nih.gov/40039793"},"language":"en","primary_location":{"id":"doi:10.1109/embc53108.2024.10782952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc53108.2024.10782952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5023279352","display_name":"Roneel V. Sharan","orcid":"https://orcid.org/0000-0003-1079-8709"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Roneel V. Sharan","raw_affiliation_strings":["University of Essex,School of Computer Science and Electronic Engineering,Colchester,United Kingdom,CO4 3SQ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Essex,School of Computer Science and Electronic Engineering,Colchester,United Kingdom,CO4 3SQ","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010623957","display_name":"Cecilia Mascolo","orcid":"https://orcid.org/0000-0001-9614-4380"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cecilia Mascolo","raw_affiliation_strings":["University of Cambridge,Department of Computer Science and Technology,Cambridge,United Kingdom,CB3 0FD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge,Department of Computer Science and Technology,Cambridge,United Kingdom,CB3 0FD","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Imperial College London,GLAM – Group on Language, Audio, & Music,London,United Kingdom,WC1E 6BT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,GLAM – Group on Language, Audio, & Music,London,United Kingdom,WC1E 6BT","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023279352"],"corresponding_institution_ids":["https://openalex.org/I110002522"],"apc_list":null,"apc_paid":null,"fwci":0.9403,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76085341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2024","issue":null,"first_page":"1","last_page":"4"},"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":0.9994999766349792,"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":0.9979000091552734,"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/spectrogram","display_name":"Spectrogram","score":0.9177422523498535},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7805914878845215},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6706651449203491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.666151762008667},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6431686282157898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4213109314441681},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33582931756973267},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1335185170173645}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9177422523498535},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7805914878845215},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6706651449203491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.666151762008667},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6431686282157898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4213109314441681},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33582931756973267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1335185170173645}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013018","descriptor_name":"Sound Spectrography","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/embc53108.2024.10782952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc53108.2024.10782952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-article"},{"id":"pmid:40039793","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40039793","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1604034532","https://openalex.org/W2103869314","https://openalex.org/W2187089797","https://openalex.org/W2526050071","https://openalex.org/W2578895956","https://openalex.org/W2593116425","https://openalex.org/W2915760784","https://openalex.org/W3081192838","https://openalex.org/W3089365109","https://openalex.org/W4247068223","https://openalex.org/W4297775537","https://openalex.org/W4308216448","https://openalex.org/W4372260013","https://openalex.org/W4378175040","https://openalex.org/W4388853930","https://openalex.org/W4390481699","https://openalex.org/W6631190155","https://openalex.org/W6737664043"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W1923358586","https://openalex.org/W2184242386","https://openalex.org/W2325729322","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,117],"recognition":[2],"(SER)":[3],"in":[4,103,152],"health":[5],"applications":[6],"can":[7],"offer":[8],"several":[9],"benefits":[10],"by":[11],"providing":[12],"insights":[13],"into":[14,46,53],"the":[15,33,43,59,95,99,120,147],"emotional":[16,154],"well-being":[17],"of":[18,32,89,101,131,149],"individuals.":[19],"In":[20,39,78],"this":[21],"work,":[22],"we":[23,41,80],"propose":[24],"a":[25,54,63,82,87,139],"method":[26,109,151],"for":[27,68],"SER":[28,125],"using":[29,156],"time-frequency":[30],"representation":[31],"speech":[34,44,105,157],"signals":[35,45],"and":[36,49,115,119,133,145],"neural":[37,66,91],"networks.":[38],"particular,":[40],"divide":[42],"overlapping":[47],"segments":[48],"transform":[50],"each":[51,76,104],"segment":[52],"Mel-spectrogram.":[55,77],"The":[56,107],"Mel-spectrogram":[57],"forms":[58],"input":[60],"to":[61,93],"YAMNet,":[62],"pretrained":[64],"convolutional":[65],"network":[67],"audio":[69],"classification,":[70],"which":[71],"learns":[72],"spectral":[73],"characteristics":[74],"within":[75],"addition,":[79],"utilize":[81],"long":[83],"short-term":[84],"memory":[85],"network,":[86,92],"type":[88],"recurrent":[90],"learn":[94],"temporal":[96],"dependencies":[97],"between":[98],"sequence":[100],"Mel-spectrograms":[102],"signal.":[106],"proposed":[108],"is":[110],"evaluated":[111],"on":[112,123],"angry,":[113],"happy,":[114],"sad":[116],"types,":[118],"neutral":[121],"expression,":[122],"two":[124],"datasets,":[126],"achieving":[127],"an":[128],"average":[129],"accuracy":[130],"0.711":[132],"0.780,":[134],"respectively.":[135],"These":[136],"results":[137],"are":[138],"relative":[140],"improvement":[141],"over":[142],"baseline":[143],"methods":[144],"demonstrate":[146],"potential":[148],"our":[150],"detecting":[153],"states":[155],"signals.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}