{"id":"https://openalex.org/W4400315074","doi":"https://doi.org/10.1109/isivc61350.2024.10577886","title":"Multi-features learning via Attention-BLSTM for Speech Emotion Recognition","display_name":"Multi-features learning via Attention-BLSTM for Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-05-21","ids":{"openalex":"https://openalex.org/W4400315074","doi":"https://doi.org/10.1109/isivc61350.2024.10577886"},"language":"en","primary_location":{"id":"doi:10.1109/isivc61350.2024.10577886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isivc61350.2024.10577886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 12th International Symposium on Signal, Image, Video and Communications (ISIVC)","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/A5020331433","display_name":"Adil Chakhtouna","orcid":"https://orcid.org/0000-0001-5280-6020"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Adil Chakhtouna","raw_affiliation_strings":["Hassan II University,Team Data Science & Artificial Intelligence, Laboratory of Mathematics, Computer Science and Applications (LMCSA), Faculty of Sciences and Technologies,Mohammedia,Morocco"],"affiliations":[{"raw_affiliation_string":"Hassan II University,Team Data Science & Artificial Intelligence, Laboratory of Mathematics, Computer Science and Applications (LMCSA), Faculty of Sciences and Technologies,Mohammedia,Morocco","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067618393","display_name":"Sara Sekkate","orcid":"https://orcid.org/0000-0002-9413-3829"},"institutions":[{"id":"https://openalex.org/I99297268","display_name":"University of Hassan II Casablanca","ror":"https://ror.org/001q4kn48","country_code":"MA","type":"education","lineage":["https://openalex.org/I99297268"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Sara Sekkate","raw_affiliation_strings":["Hassan II University,Higher National School of Arts and Crafts,Casablanca,Morocco"],"affiliations":[{"raw_affiliation_string":"Hassan II University,Higher National School of Arts and Crafts,Casablanca,Morocco","institution_ids":["https://openalex.org/I99297268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032292618","display_name":"Abdellah Adib","orcid":"https://orcid.org/0000-0002-0670-7221"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdellah Adib","raw_affiliation_strings":["Hassan II University,Team Data Science & Artificial Intelligence, Laboratory of Mathematics, Computer Science and Applications (LMCSA), Faculty of Sciences and Technologies,Mohammedia,Morocco"],"affiliations":[{"raw_affiliation_string":"Hassan II University,Team Data Science & Artificial Intelligence, Laboratory of Mathematics, Computer Science and Applications (LMCSA), Faculty of Sciences and Technologies,Mohammedia,Morocco","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020331433"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4942,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82009959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.839900016784668,"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/T10860","display_name":"Speech and Audio Processing","score":0.839900016784668,"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":0.8190000057220459,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7603999972343445,"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/computer-science","display_name":"Computer science","score":0.7789103984832764},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.737255334854126},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6236358880996704},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3658156991004944},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3627152442932129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789103984832764},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.737255334854126},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6236358880996704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3658156991004944},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3627152442932129}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isivc61350.2024.10577886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isivc61350.2024.10577886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 12th International Symposium on Signal, Image, Video and Communications (ISIVC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321147","display_name":"Ministry of Higher Education","ror":"https://ror.org/0512bh102"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2085662862","https://openalex.org/W2131774270","https://openalex.org/W2146334809","https://openalex.org/W2148154194","https://openalex.org/W2703895418","https://openalex.org/W2750666523","https://openalex.org/W2766756589","https://openalex.org/W2885005742","https://openalex.org/W2896457183","https://openalex.org/W2959546144","https://openalex.org/W2970737019","https://openalex.org/W2972452068","https://openalex.org/W2973181312","https://openalex.org/W2997399314","https://openalex.org/W2999905431","https://openalex.org/W3004344051","https://openalex.org/W3015884429","https://openalex.org/W3043469888","https://openalex.org/W3076928706","https://openalex.org/W3084484668","https://openalex.org/W3095648847","https://openalex.org/W3097969370","https://openalex.org/W3128401974","https://openalex.org/W3155872272","https://openalex.org/W3198429080","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211224152","https://openalex.org/W4221013626","https://openalex.org/W4293799794","https://openalex.org/W4306938603","https://openalex.org/W4309240333","https://openalex.org/W4386071707","https://openalex.org/W4386156746","https://openalex.org/W4389057691","https://openalex.org/W6755207826","https://openalex.org/W6780218876","https://openalex.org/W6803378298"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Within":[0],"the":[1,15,31,40,52,66,78,94,122,137,141,164],"domain":[2],"of":[3,18,33,42,60,68,97,106,158],"human-computer":[4],"interaction,":[5],"Speech":[6],"Emotion":[7],"Recognition":[8],"(SER)":[9],"has":[10],"assumed":[11],"critical":[12],"importance,":[13],"where":[14],"careful":[16],"selection":[17],"feature":[19],"representation":[20],"stands":[21],"as":[22],"a":[23,35,43,103],"key":[24],"determinant.":[25],"This":[26,161],"study":[27],"is":[28],"driven":[29],"by":[30,147],"objective":[32],"conducting":[34],"comprehensive":[36],"comparative":[37],"analysis":[38],"through":[39,128],"implementation":[41],"parallel":[44],"multi-feature":[45],"design,":[46],"strategically":[47],"aimed":[48],"to":[49,92,101,118],"effectively":[50],"characterize":[51],"emotional":[53,124],"information":[54],"within":[55],"speech":[56,125],"signals.":[57],"The":[58,131],"innovation":[59],"our":[61,152],"proposed":[62,153],"approach":[63],"lies":[64],"in":[65,168],"integration":[67],"frameworks,":[69],"including":[70],"ImageBind,":[71],"WavLM,":[72],"HuBERT,":[73],"Wav2vec":[74],"2-xlsr,":[75],"along":[76],"with":[77,151],"commonly":[79],"used":[80],"MFCC":[81],"features.":[82],"Leveraging":[83],"their":[84],"knowledge":[85],"and":[86,120,140],"adaptability,":[87],"we":[88,108],"tailor":[89],"these":[90],"frameworks":[91],"meet":[93],"specific":[95],"demands":[96],"SER":[98],"task.":[99],"Furthermore,":[100],"encompass":[102],"rich":[104],"set":[105],"multi-features,":[107],"introduced":[109],"an":[110,156],"Attention-based":[111],"Bidirectional":[112],"Long":[113],"ShortTerm":[114],"Memory":[115],"(attention-BLSTM)":[116],"network":[117],"capture":[119],"learn":[121],"distinct":[123],"representations":[126],"extracted":[127],"various":[129],"methods.":[130],"experimental":[132],"evaluations":[133],"were":[134,145],"executed":[135],"using":[136],"IEMOCAP":[138],"database,":[139],"most":[142],"remarkable":[143],"results":[144],"attained":[146],"employing":[148],"ImageBind":[149],"embeddings":[150],"attention-BLSTM,":[154],"achieving":[155],"accuracy":[157],"$81.03":[159],"\\%$.":[160],"outcome":[162],"outshines":[163],"current":[165],"state-of-the-art":[166],"approaches":[167],"SER.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}