{"id":"https://openalex.org/W4414458967","doi":"https://doi.org/10.1109/access.2025.3614020","title":"A Multimodal Deep Network for Music Emotion Recognition Using Audio Chorus and Lyrics","display_name":"A Multimodal Deep Network for Music Emotion Recognition Using Audio Chorus and Lyrics","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414458967","doi":"https://doi.org/10.1109/access.2025.3614020"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3614020","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3614020","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3614020","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092424746","display_name":"Mohammad Ali Talaghat","orcid":"https://orcid.org/0000-0003-2687-3988"},"institutions":[{"id":"https://openalex.org/I91138267","display_name":"Islamic Azad University of Shiraz","ror":"https://ror.org/03xbchh53","country_code":"IR","type":"education","lineage":["https://openalex.org/I110525433","https://openalex.org/I91138267"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Mohammad Ali Talaghat","raw_affiliation_strings":["Department of Computer Engineering, Shi.C., Islamic Azad University, Shiraz, Iran"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Shi.C., Islamic Azad University, Shiraz, Iran","institution_ids":["https://openalex.org/I91138267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065423251","display_name":"Elham Parvinnia","orcid":"https://orcid.org/0000-0002-4728-5483"},"institutions":[{"id":"https://openalex.org/I91138267","display_name":"Islamic Azad University of Shiraz","ror":"https://ror.org/03xbchh53","country_code":"IR","type":"education","lineage":["https://openalex.org/I110525433","https://openalex.org/I91138267"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Elham Parvinnia","raw_affiliation_strings":["Department of Computer Engineering, Shi.C., Islamic Azad University, Shiraz, Iran"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Shi.C., Islamic Azad University, Shiraz, Iran","institution_ids":["https://openalex.org/I91138267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043213314","display_name":"Mahdi Mehrabi","orcid":"https://orcid.org/0000-0002-1551-5723"},"institutions":[{"id":"https://openalex.org/I91138267","display_name":"Islamic Azad University of Shiraz","ror":"https://ror.org/03xbchh53","country_code":"IR","type":"education","lineage":["https://openalex.org/I110525433","https://openalex.org/I91138267"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mahdi Mehrabi","raw_affiliation_strings":["Department of Computer Engineering, Shi.C., Islamic Azad University, Shiraz, Iran"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Shi.C., Islamic Azad University, Shiraz, Iran","institution_ids":["https://openalex.org/I91138267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079098947","display_name":"Reza Boostani","orcid":"https://orcid.org/0000-0003-0055-4452"},"institutions":[{"id":"https://openalex.org/I166459259","display_name":"Shiraz University","ror":"https://ror.org/028qtbk54","country_code":"IR","type":"education","lineage":["https://openalex.org/I166459259"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Reza Boostani","raw_affiliation_strings":["Department of Computer Science Engineering and Information Technology, Shiraz University, Shiraz, Iran","Department of CSE&IT, Faculty of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science Engineering and Information Technology, Shiraz University, Shiraz, Iran","institution_ids":["https://openalex.org/I166459259"]},{"raw_affiliation_string":"Department of CSE&IT, Faculty of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran","institution_ids":["https://openalex.org/I166459259"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5092424746"],"corresponding_institution_ids":["https://openalex.org/I91138267"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.6611,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87125387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":null,"first_page":"177509","last_page":"177519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9958000183105469,"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":0.9958000183105469,"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":0.982200026512146,"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":0.9480000138282776,"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/lyrics","display_name":"Lyrics","score":0.8637999892234802},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6840999722480774},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6365000009536743},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6201000213623047},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5493999719619751},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5213000178337097},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4797999858856201},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.3935999870300293}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.8637999892234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570000290870667},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6840999722480774},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6462000012397766},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6365000009536743},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5493999719619751},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5213000178337097},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4456000030040741},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3686000108718872},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.27489998936653137}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3614020","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3614020","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2bb7d99348494bf19cf4d9f4a3493a8c","is_oa":true,"landing_page_url":"https://doaj.org/article/2bb7d99348494bf19cf4d9f4a3493a8c","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 177509-177519 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3614020","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3614020","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W1994477474","https://openalex.org/W2042266440","https://openalex.org/W2069682406","https://openalex.org/W2123991323","https://openalex.org/W2149628368","https://openalex.org/W2171848217","https://openalex.org/W2523856713","https://openalex.org/W2592535880","https://openalex.org/W2945956523","https://openalex.org/W2972819746","https://openalex.org/W2977423666","https://openalex.org/W2999606367","https://openalex.org/W3046491228","https://openalex.org/W3091273176","https://openalex.org/W3094144570","https://openalex.org/W3098740611","https://openalex.org/W3107698614","https://openalex.org/W3161428216","https://openalex.org/W3162686331","https://openalex.org/W3189205145","https://openalex.org/W3200673119","https://openalex.org/W4200404613","https://openalex.org/W4206908116","https://openalex.org/W4210248471","https://openalex.org/W4214825215","https://openalex.org/W4247068223","https://openalex.org/W4283808392","https://openalex.org/W4297675714","https://openalex.org/W4308478537","https://openalex.org/W4313334373","https://openalex.org/W4321105107","https://openalex.org/W4385245566","https://openalex.org/W4394879572","https://openalex.org/W4403635995"],"related_works":[],"abstract_inverted_index":{"Music":[0],"emotion":[1,36,123],"recognition":[2,37,124],"(MER)":[3],"is":[4,90,114],"an":[5,52],"essential":[6],"branch":[7],"in":[8,49,119,139],"music":[9,16],"information":[10],"retrieval,":[11],"focusing":[12],"on":[13,18],"categorization":[14],"of":[15,74,130],"based":[17],"emotional":[19],"content.":[20],"This":[21],"study":[22],"introduces":[23],"a":[24,77],"multimodal":[25,137],"deep":[26,133],"learning":[27],"architecture":[28],"adopting":[29],"audio":[30],"and":[31,71,88,92,99,136],"lyrics":[32,105],"to":[33,54,116],"improve":[34],"the":[35,66,68,111,128],"accuracy.":[38],"The":[39],"model":[40],"employs":[41],"convolutional":[42],"neural":[43],"networks,":[44,135],"long":[45],"short-term":[46],"memory":[47],"layers,":[48],"addition":[50],"with":[51],"attention":[53,134],"emphasize":[55],"emotionally":[56],"salient":[57],"features.":[58],"Significant":[59],"performance":[60],"gains":[61],"are":[62,84,102],"achieved":[63],"by":[64,86,97],"analyzing":[65],"chorus\u2014often":[67],"most":[69],"expressive":[70],"repetitive":[72],"part":[73],"music.":[75],"Herein,":[76],"new":[78],"dataset":[79],"containing":[80],"9,087":[81],"tracks":[82],"which":[83,126],"labeled":[85],"valence":[87],"arousal,":[89],"prepared":[91],"introduced.":[93],"Moreover,":[94],"embeddings":[95],"generated":[96],"XLNet":[98],"BERT":[100],"networks":[101],"compared":[103],"for":[104],"feature":[106],"extraction.":[107],"Experimental":[108],"results":[109],"demonstrate":[110],"proposed":[112],"scheme":[113],"superior":[115,122],"state-of-the-art":[117],"methods":[118],"achieving":[120],"significantly":[121],"accuracy,":[125],"underscores":[127],"value":[129],"chorus-based":[131],"analysis,":[132],"integration":[138],"advancing":[140],"MER.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}