{"id":"https://openalex.org/W4408353751","doi":"https://doi.org/10.1109/icassp49660.2025.10887873","title":"Multi-Microphone Speech Emotion Recognition Using the Hierarchical Token-Semantic Audio Transformer Architecture","display_name":"Multi-Microphone Speech Emotion Recognition Using the Hierarchical Token-Semantic Audio Transformer Architecture","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353751","doi":"https://doi.org/10.1109/icassp49660.2025.10887873"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5111223594","display_name":"Ohad Cohen","orcid":"https://orcid.org/0009-0002-4707-881X"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ohad Cohen","raw_affiliation_strings":["Bar-Ilan University,Faculty of Engineering,Ramat-Gan,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University,Faculty of Engineering,Ramat-Gan,Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022085824","display_name":"Gershon Hazan","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gershon Hazan","raw_affiliation_strings":["Bar-Ilan University,Faculty of Engineering,Ramat-Gan,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University,Faculty of Engineering,Ramat-Gan,Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001052072","display_name":"Sharon Gannot","orcid":"https://orcid.org/0000-0002-2885-170X"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sharon Gannot","raw_affiliation_strings":["Bar-Ilan University,Faculty of Engineering,Ramat-Gan,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University,Faculty of Engineering,Ramat-Gan,Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1921,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.90577477,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9797999858856201,"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":0.9797999858856201,"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/T11309","display_name":"Music and Audio Processing","score":0.9616000056266785,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8125443458557129},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6766812205314636},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6266680359840393},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5885071754455566},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5654156804084778},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.537499189376831},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15834635496139526},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08282962441444397},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06508594751358032},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06033441424369812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8125443458557129},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6766812205314636},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6266680359840393},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5885071754455566},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5654156804084778},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.537499189376831},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15834635496139526},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08282962441444397},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06508594751358032},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06033441424369812},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2146334809","https://openalex.org/W2394573230","https://openalex.org/W2403254325","https://openalex.org/W2410879554","https://openalex.org/W2578895956","https://openalex.org/W2593116425","https://openalex.org/W2750666523","https://openalex.org/W2785960144","https://openalex.org/W2802039619","https://openalex.org/W2889332211","https://openalex.org/W2889544113","https://openalex.org/W2915189764","https://openalex.org/W2936774411","https://openalex.org/W2964370293","https://openalex.org/W3014556410","https://openalex.org/W3081192838","https://openalex.org/W3092557781","https://openalex.org/W3109961563","https://openalex.org/W3111613338","https://openalex.org/W3138516171","https://openalex.org/W3163652268","https://openalex.org/W3196974791","https://openalex.org/W4226442948","https://openalex.org/W4293261951","https://openalex.org/W4312120856","https://openalex.org/W4385245566","https://openalex.org/W4388118363","https://openalex.org/W4404577251","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W107154053","https://openalex.org/W4304700937"],"abstract_inverted_index":{"The":[0],"performance":[1,30,95],"of":[2,32],"most":[3],"emotion":[4,58],"recognition":[5],"systems":[6],"degrades":[7],"in":[8],"real-life":[9],"situations":[10],"(\"in":[11],"the":[12,16,29,67],"wild\"":[13],"scenarios)":[14],"where":[15],"audio":[17,76],"is":[18],"contaminated":[19],"by":[20],"reverberation.":[21],"Our":[22,90],"study":[23],"explores":[24],"new":[25],"methods":[26],"to":[27,52,73,97],"alleviate":[28],"degradation":[31],"Speech":[33],"Emotion":[34],"Recognition":[35],"(SER)":[36],"algorithms":[37],"and":[38,56,86],"develop":[39],"a":[40,63],"more":[41],"robust":[42],"system":[43],"for":[44],"adverse":[45],"conditions.":[46],"We":[47,61,78],"propose":[48],"processing":[49],"multi-microphone":[50,91],"signals":[51],"address":[53],"these":[54],"challenges":[55],"improve":[57],"classification":[59],"accuracy.":[60],"adopt":[62],"state-of-the-art":[64],"transformer":[65],"model,":[66],"Hierarchical":[68],"Token-semantic":[69],"Audio":[70],"Transformer":[71],"(HTS-AT),":[72],"handle":[74],"multi-channel":[75],"inputs.":[77],"evaluate":[79],"two":[80],"strategies:":[81],"averaging":[82],"mel-spectrograms":[83],"across":[84],"channels":[85],"summing":[87],"patch-embedded":[88],"representations.":[89],"model":[92],"achieves":[93],"superior":[94],"compared":[96],"single-channel":[98],"baselines":[99],"when":[100],"tested":[101],"on":[102],"real-world":[103],"reverberant":[104],"environments.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}