{"id":"https://openalex.org/W4385626707","doi":"https://doi.org/10.1109/dese58274.2023.10100058","title":"Deep Audio Embeddings and Attention Based Music Emotion Recognition","display_name":"Deep Audio Embeddings and Attention Based Music Emotion Recognition","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4385626707","doi":"https://doi.org/10.1109/dese58274.2023.10100058"},"language":"en","primary_location":{"id":"doi:10.1109/dese58274.2023.10100058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dese58274.2023.10100058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102464099","display_name":"Sparsh Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I63098007","display_name":"Liverpool John Moores University","ror":"https://ror.org/04zfme737","country_code":"GB","type":"education","lineage":["https://openalex.org/I63098007"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Sparsh Gupta","raw_affiliation_strings":["Liverpool John Moores University,Liverpool,UK","Liverpool John Moores University, Liverpool, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Liverpool John Moores University,Liverpool,UK","institution_ids":["https://openalex.org/I63098007"]},{"raw_affiliation_string":"Liverpool John Moores University, Liverpool, UK","institution_ids":["https://openalex.org/I63098007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5102464099"],"corresponding_institution_ids":["https://openalex.org/I63098007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"357","last_page":"362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10788","display_name":"Neuroscience and Music Perception","score":0.9726999998092651,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.970300018787384,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.8039436340332031},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6944316029548645},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6410311460494995},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5461588501930237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5377485752105713},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.535624623298645},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.5269433259963989},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.5243352055549622},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4781978130340576},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4516248106956482},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.43450722098350525},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4132747948169708},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.26073068380355835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039436340332031},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6944316029548645},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6410311460494995},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5461588501930237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5377485752105713},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.535624623298645},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.5269433259963989},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.5243352055549622},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4781978130340576},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4516248106956482},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.43450722098350525},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4132747948169708},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.26073068380355835},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dese58274.2023.10100058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dese58274.2023.10100058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 15th International Conference on Developments in eSystems Engineering (DeSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W41198089","https://openalex.org/W1966797434","https://openalex.org/W1983507146","https://openalex.org/W2032018075","https://openalex.org/W2038678505","https://openalex.org/W2045456197","https://openalex.org/W2072691998","https://openalex.org/W2081835714","https://openalex.org/W2103662883","https://openalex.org/W2135949113","https://openalex.org/W2136129419","https://openalex.org/W2149628368","https://openalex.org/W2293932197","https://openalex.org/W2293996892","https://openalex.org/W2405190343","https://openalex.org/W2756184659","https://openalex.org/W2785930174","https://openalex.org/W2789063610","https://openalex.org/W2795014578","https://openalex.org/W2939574508","https://openalex.org/W2972819746","https://openalex.org/W2988011080","https://openalex.org/W3092043977","https://openalex.org/W3098740611","https://openalex.org/W3102163718","https://openalex.org/W3119316801","https://openalex.org/W3192490616","https://openalex.org/W4293258764","https://openalex.org/W4293665662","https://openalex.org/W4385245566","https://openalex.org/W6638667902","https://openalex.org/W6729831399","https://openalex.org/W6737778391","https://openalex.org/W6738953990","https://openalex.org/W6794667172"],"related_works":["https://openalex.org/W3082895349","https://openalex.org/W4327774331","https://openalex.org/W2480330148","https://openalex.org/W2787045460","https://openalex.org/W2919358988","https://openalex.org/W3011995931","https://openalex.org/W2793022090","https://openalex.org/W4298168912","https://openalex.org/W4315783664","https://openalex.org/W4384074436"],"abstract_inverted_index":{"The":[0,22,103,142],"emotion":[1,23,87,91],"is":[2,11,27,94],"an":[3,28],"intricated":[4],"impression":[5],"present":[6],"in":[7,96,156],"the":[8,53,62,84,100,114,148,153,157,168,178,183],"music":[9,42],"that":[10,31,118,167],"extremely":[12],"hard":[13],"to":[14,151],"capture":[15],"even":[16],"using":[17,68,83,182],"refined":[18],"feature":[19,30,123],"engineering":[20,124],"techniques.":[21],"of":[24,55,180],"a":[25,80],"song":[26],"important":[29],"can":[32],"be":[33],"used":[34,95,110],"for":[35,71,113],"various":[36],"MIR":[37],"tasks":[38],"like":[39],"recommendation":[40],"systems,":[41],"therapy,":[43],"and":[44,89,125,138],"automatic":[45],"playlist":[46],"generation.":[47],"In":[48,75],"this":[49,97],"research,":[50],"we":[51,77,165],"investigate":[52],"application":[54],"L3-":[56],"Net":[57],"deep":[58,64,105],"audio":[59,86,106,158],"embeddings":[60,107,159],"with":[61,137,177],"attention-based":[63,133],"neural":[65,115,134],"network":[66,116,135],"model":[67,117,150,170],"positional":[69,143],"encoding":[70,144],"recognizing":[72],"musical":[73],"emotions.":[74],"addition,":[76],"have":[78,130],"constructed":[79],"master":[81],"dataset":[82,88,92],"4Q":[85],"Bi-modal":[90],"which":[93],"research":[98],"as":[99,111],"main":[101],"dataset.":[102],"L3-Net":[104],"are":[108],"being":[109],"features":[112],"does":[119],"not":[120],"require":[121],"any":[122,161],"other":[126,175],"audio-based":[127],"features.":[128],"We":[129],"proposed":[131],"two":[132],"models":[136,176],"without":[139,160],"recurrent":[140,154,162],"layers.":[141,163],"mechanism":[145],"has":[146,171],"helped":[147],"ACNN":[149,169],"learn":[152],"information":[155],"Therefore,":[164],"conclude":[166],"performed":[172],"better":[173],"than":[174],"F1-score":[179],"0.79":[181],"AdamP":[184],"optimizer.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}