{"id":"https://openalex.org/W4404037445","doi":"https://doi.org/10.1109/mlsp58920.2024.10734746","title":"TBDM-NET: Bidirectional Dense Networks with Gender Information for Speech Emotion Recognition","display_name":"TBDM-NET: Bidirectional Dense Networks with Gender Information for Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-09-22","ids":{"openalex":"https://openalex.org/W4404037445","doi":"https://doi.org/10.1109/mlsp58920.2024.10734746"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp58920.2024.10734746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp58920.2024.10734746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5093266199","display_name":"Vlad Strile\u021bchi","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Vlad Striletchi","raw_affiliation_strings":["Technical University of Cluj-Napoca,Communications Department,Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Communications Department,Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017426641","display_name":"Cosmin Strile\u0163chi","orcid":"https://orcid.org/0000-0002-5663-9159"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Cosmin Striletchi","raw_affiliation_strings":["Technical University of Cluj-Napoca,Communications Department,Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Communications Department,Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Technical University of Cluj-Napoca,Communications Department,Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Communications Department,Romania","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093266199"],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":1.4504,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85367445,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9514999985694885,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9514999985694885,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9373999834060669,"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":0.9240000247955322,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.707319974899292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6127209067344666},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5688230991363525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707319974899292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6127209067344666},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5688230991363525}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp58920.2024.10734746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp58920.2024.10734746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W589698015","https://openalex.org/W2054857826","https://openalex.org/W2146334809","https://openalex.org/W2399733683","https://openalex.org/W2578895956","https://openalex.org/W2726515241","https://openalex.org/W2803193013","https://openalex.org/W2899663614","https://openalex.org/W2959546144","https://openalex.org/W2963446712","https://openalex.org/W3093739508","https://openalex.org/W3094995278","https://openalex.org/W3204087964","https://openalex.org/W3205878676","https://openalex.org/W4221162793","https://openalex.org/W4307273323","https://openalex.org/W4372269797","https://openalex.org/W4377009115","https://openalex.org/W4379033883","https://openalex.org/W4385822846","https://openalex.org/W4401050382","https://openalex.org/W6617505242","https://openalex.org/W6755977528","https://openalex.org/W6811070765","https://openalex.org/W6846256037"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"This":[0,45],"paper":[1],"presents":[2],"a":[3,59],"novel":[4],"deep":[5],"neural":[6],"network-based":[7],"architecture":[8,16,47],"tailored":[9],"for":[10,74],"Speech":[11],"Emotion":[12],"Recognition":[13],"(SER).":[14],"The":[15,102],"capitalises":[17],"on":[18],"dense":[19],"interconnections":[20],"among":[21],"multiple":[22],"layers":[23,37],"of":[24,35,63,84,104],"bidirectional":[25],"dilated":[26],"convolutions.":[27],"A":[28],"linear":[29],"kernel":[30],"dynamically":[31],"fuses":[32],"the":[33,40,82,97],"outputs":[34],"these":[36],"to":[38,96],"yield":[39],"final":[41],"emotion":[42,77,86],"class":[43],"prediction.":[44],"innovative":[46],"is":[48,106],"denoted":[49],"as":[50],"TBDM-Net:":[51],"Temporally-Aware":[52],"Bi-directional":[53],"Dense":[54],"Multi-Scale":[55],"Network.":[56],"We":[57],"conduct":[58],"comprehensive":[60],"performance":[61],"evaluation":[62],"TBDM-Net,":[64],"including":[65],"an":[66],"ablation":[67],"study,":[68],"across":[69],"six":[70],"widely-acknowledged":[71],"SER":[72],"datasets":[73],"unimodal":[75],"speech":[76],"recognition.":[78],"Additionally,":[79],"we":[80],"explore":[81],"influence":[83],"gender-informed":[85],"prediction":[87],"by":[88],"appending":[89],"either":[90],"golden":[91],"or":[92,100],"predicted":[93],"gender":[94],"labels":[95],"architecture's":[98],"inputs":[99],"predictions.":[101],"implementation":[103],"TBDM-Net":[105],"accessible":[107],"at:":[108],"https://github.com/adrianastan/tbdm-net.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}