{"id":"https://openalex.org/W4415433713","doi":"https://doi.org/10.21437/interspeech.2025-418","title":"Multi-Teacher Language-Aware Knowledge Distillation for Multilingual Speech Emotion Recognition","display_name":"Multi-Teacher Language-Aware Knowledge Distillation for Multilingual Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433713","doi":"https://doi.org/10.21437/interspeech.2025-418"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-418","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.08717","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000945812","display_name":"Mehedi Hasan Bijoy","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mehedi Hasan Bijoy","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052292328","display_name":"Dejan Porjazovski","orcid":"https://orcid.org/0000-0002-7219-9042"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dejan Porjazovski","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058277119","display_name":"Tam\u00e1s Gr\u00f3sz","orcid":"https://orcid.org/0000-0001-7918-9579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tam\u00e1s Gr\u00f3sz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000945812"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16713668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8810999989509583,"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":0.8810999989509583,"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":0.8479999899864197,"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/T12031","display_name":"Speech and dialogue systems","score":0.8392999768257141,"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/recall","display_name":"Recall","score":0.7671999931335449},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5267000198364258},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.3991999924182892},{"id":"https://openalex.org/keywords/anger","display_name":"Anger","score":0.39089998602867126},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.3659000098705292},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.3353999853134155}],"concepts":[{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.7671999931335449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7138000130653381},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6384999752044678},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.515500009059906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4528999924659729},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C2779302386","wikidata":"https://www.wikidata.org/wiki/Q79871","display_name":"Anger","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C49929091","wikidata":"https://www.wikidata.org/wiki/Q1930471","display_name":"General knowledge","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C84685590","wikidata":"https://www.wikidata.org/wiki/Q1540472","display_name":"Knowledge engineering","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-418","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.08717","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.08717","pdf_url":"https://arxiv.org/pdf/2506.08717","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.08717","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.08717","pdf_url":"https://arxiv.org/pdf/2506.08717","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"is":[4,26],"crucial":[5],"for":[6,122],"improving":[7,120],"human-computer":[8],"interaction.":[9],"Despite":[10],"strides":[11],"in":[12,58,119,132],"monolingual":[13,70],"SER,":[14],"extending":[15],"them":[16],"to":[17,27,55],"build":[18],"a":[19,29,48,79,91],"multilingual":[20,34,81],"system":[21],"remains":[22],"challenging.":[23],"Our":[24,116],"goal":[25],"train":[28],"single":[30,80],"model":[31,86],"capable":[32],"of":[33,69,94,104],"SER":[35,57],"by":[36],"distilling":[37],"knowledge":[38,52,77,113],"from":[39],"multiple":[40],"teacher":[41,71],"models.":[42],"To":[43],"address":[44],"this,":[45],"we":[46],"introduce":[47],"novel":[49],"language-aware":[50],"multi-teacher":[51],"distillation":[53,114],"method":[54,117],"advance":[56],"English,":[59],"Finnish,":[60],"and":[61,73,100,112,124,135],"French.":[62],"It":[63],"leverages":[64],"Wav2Vec2.0":[65],"as":[66],"the":[67,97,107],"foundation":[68],"models":[72],"then":[74],"distills":[75],"their":[76],"into":[78],"student":[82,85],"model.":[83],"The":[84],"demonstrates":[87],"state-of-the-art":[88],"performance,":[89],"with":[90],"weighted":[92],"recall":[93,103,121],"72.9":[95],"on":[96,106],"English":[98],"dataset":[99],"an":[101],"unweighted":[102],"63.4":[105],"Finnish":[108],"dataset,":[109],"surpassing":[110],"fine-tuning":[111],"baselines.":[115],"excels":[118],"sad":[123],"neutral":[125],"emotions,":[126],"although":[127],"it":[128],"still":[129],"faces":[130],"challenges":[131],"recognizing":[133],"anger":[134],"happiness.":[136]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-23T00:00:00"}