{"id":"https://openalex.org/W4390345824","doi":"https://doi.org/10.1007/s10772-023-10079-0","title":"Deep neural network architectures for audio emotion recognition performed on song and speech modalities","display_name":"Deep neural network architectures for audio emotion recognition performed on song and speech modalities","publication_year":2023,"publication_date":"2023-12-01","ids":{"openalex":"https://openalex.org/W4390345824","doi":"https://doi.org/10.1007/s10772-023-10079-0"},"language":"en","primary_location":{"id":"doi:10.1007/s10772-023-10079-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-023-10079-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-023-10079-0.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s10772-023-10079-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085474357","display_name":"Souha Ayadi","orcid":"https://orcid.org/0000-0002-6389-8933"},"institutions":[{"id":"https://openalex.org/I4210131288","display_name":"National Engineering School of Tunis","ror":"https://ror.org/03b1zjt31","country_code":"TN","type":"education","lineage":["https://openalex.org/I4210131288","https://openalex.org/I63596082"]},{"id":"https://openalex.org/I63596082","display_name":"Tunis El Manar University","ror":"https://ror.org/029cgt552","country_code":"TN","type":"education","lineage":["https://openalex.org/I63596082"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Souha Ayadi","raw_affiliation_strings":["Signal Image and Information Technology Laboratory (SITI), Department Electrical Engineering, National School of Engineers (ENIT), University of Tunis el Manar, BP 37,le Belv\u00e8d\u00e8re, 1002, Tunis, Tunisia"],"raw_orcid":"https://orcid.org/0000-0002-6389-8933","affiliations":[{"raw_affiliation_string":"Signal Image and Information Technology Laboratory (SITI), Department Electrical Engineering, National School of Engineers (ENIT), University of Tunis el Manar, BP 37,le Belv\u00e8d\u00e8re, 1002, Tunis, Tunisia","institution_ids":["https://openalex.org/I4210131288","https://openalex.org/I63596082"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063621759","display_name":"Zied Lachiri","orcid":"https://orcid.org/0000-0002-1289-5089"},"institutions":[{"id":"https://openalex.org/I4210131288","display_name":"National Engineering School of Tunis","ror":"https://ror.org/03b1zjt31","country_code":"TN","type":"education","lineage":["https://openalex.org/I4210131288","https://openalex.org/I63596082"]},{"id":"https://openalex.org/I63596082","display_name":"Tunis El Manar University","ror":"https://ror.org/029cgt552","country_code":"TN","type":"education","lineage":["https://openalex.org/I63596082"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Zied Lachiri","raw_affiliation_strings":["Signal Image and Information Technology Laboratory (SITI), Department Electrical Engineering, National School of Engineers (ENIT), University of Tunis el Manar, BP 37,le Belv\u00e8d\u00e8re, 1002, Tunis, Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Image and Information Technology Laboratory (SITI), Department Electrical Engineering, National School of Engineers (ENIT), University of Tunis el Manar, BP 37,le Belv\u00e8d\u00e8re, 1002, Tunis, Tunisia","institution_ids":["https://openalex.org/I4210131288","https://openalex.org/I63596082"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085474357"],"corresponding_institution_ids":["https://openalex.org/I4210131288","https://openalex.org/I63596082"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2780},"apc_paid":null,"fwci":0.5757,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66864748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"26","issue":"4","first_page":"1165","last_page":"1181"},"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":0.9986000061035156,"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":0.9868000149726868,"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":0.8931488990783691},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.7143651843070984},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.667803168296814},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6268322467803955},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6057288646697998},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5551924109458923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5450534820556641},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5185418725013733},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48631271719932556},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4731743633747101},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44662410020828247},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4440731406211853},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.44058796763420105},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4393256604671478},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3843047618865967},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.35532146692276},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.15995243191719055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8931488990783691},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7143651843070984},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.667803168296814},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6268322467803955},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6057288646697998},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5551924109458923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5450534820556641},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5185418725013733},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48631271719932556},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4731743633747101},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44662410020828247},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4440731406211853},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.44058796763420105},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4393256604671478},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3843047618865967},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.35532146692276},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.15995243191719055},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10772-023-10079-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-023-10079-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-023-10079-0.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10772-023-10079-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-023-10079-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-023-10079-0.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390345824.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W2049266248","https://openalex.org/W2062826588","https://openalex.org/W2064675550","https://openalex.org/W2083488428","https://openalex.org/W2095705004","https://openalex.org/W2119615570","https://openalex.org/W2121551440","https://openalex.org/W2122585011","https://openalex.org/W2141173017","https://openalex.org/W2295001676","https://openalex.org/W2408520939","https://openalex.org/W2510170536","https://openalex.org/W2783819197","https://openalex.org/W2803193013","https://openalex.org/W2804220026","https://openalex.org/W2889169802","https://openalex.org/W2891488835","https://openalex.org/W2959546144","https://openalex.org/W2962770129","https://openalex.org/W2993348073","https://openalex.org/W2997700007","https://openalex.org/W3006477068","https://openalex.org/W3008039831","https://openalex.org/W3009684390","https://openalex.org/W3035264762","https://openalex.org/W3084484668","https://openalex.org/W3088789516","https://openalex.org/W3094312606","https://openalex.org/W3096262466","https://openalex.org/W3109961563","https://openalex.org/W3118765838","https://openalex.org/W4220688223","https://openalex.org/W4229079244","https://openalex.org/W4283711157","https://openalex.org/W4376624979","https://openalex.org/W6601668641","https://openalex.org/W6675354045","https://openalex.org/W6749029207"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W1975359510","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3004352674","https://openalex.org/W3043119899","https://openalex.org/W3110605476","https://openalex.org/W2363106653"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-21T23:30:37.877113","created_date":"2025-10-10T00:00:00"}
