{"id":"https://openalex.org/W4408345935","doi":"https://doi.org/10.1109/icassp49660.2025.10890304","title":"Exploring Acoustic Similarity in Emotional Speech and Music via Self-Supervised Representations","display_name":"Exploring Acoustic Similarity in Emotional Speech and Music via Self-Supervised Representations","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345935","doi":"https://doi.org/10.1109/icassp49660.2025.10890304"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890304","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/A5034889746","display_name":"Yujia Sun","orcid":"https://orcid.org/0009-0003-9332-8338"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yujia Sun","raw_affiliation_strings":["University of Edinburgh,UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100775936","display_name":"Zeyu Zhao","orcid":"https://orcid.org/0009-0002-6612-9731"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zeyu Zhao","raw_affiliation_strings":["University of Edinburgh,UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Korin Richmond","raw_affiliation_strings":["University of Edinburgh,UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101930951","display_name":"Yuanchao Li","orcid":"https://orcid.org/0000-0001-8728-1295"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuanchao Li","raw_affiliation_strings":["University of Edinburgh,UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034889746"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":3.1486,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8952529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"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":0.9538000226020813,"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":0.9538000226020813,"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":0.9485999941825867,"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":0.9429000020027161,"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/speech-recognition","display_name":"Speech recognition","score":0.7151955962181091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6367356777191162},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6259830594062805},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3821644186973572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3413989543914795}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7151955962181091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6367356777191162},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6259830594062805},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3821644186973572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3413989543914795},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890304","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1442117752","https://openalex.org/W1608020191","https://openalex.org/W1983507146","https://openalex.org/W1987759408","https://openalex.org/W2021079736","https://openalex.org/W2032254851","https://openalex.org/W2072683649","https://openalex.org/W2104773730","https://openalex.org/W2189018360","https://openalex.org/W2400814905","https://openalex.org/W2735654625","https://openalex.org/W2803193013","https://openalex.org/W2972478942","https://openalex.org/W2995181338","https://openalex.org/W3113738772","https://openalex.org/W3205091761","https://openalex.org/W3209059054","https://openalex.org/W4226380987","https://openalex.org/W4319862479","https://openalex.org/W4319862652","https://openalex.org/W4375869259","https://openalex.org/W4391987579","https://openalex.org/W4392902957","https://openalex.org/W4401609030","https://openalex.org/W4408354672","https://openalex.org/W6704344484","https://openalex.org/W6759579507","https://openalex.org/W6796581206","https://openalex.org/W6810007534","https://openalex.org/W6853393314","https://openalex.org/W6873298725"],"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/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Emotion":[0,87,92],"recognition":[1],"from":[2,194],"speech":[3,30,51,71,118,129,147,157,208],"and":[4,31,52,72,90,117,130,148,158,180,188,209,211,221],"music":[5,53,114,131,149,159],"shares":[6],"similarities":[7,126],"due":[8,175],"to":[9,16,112,176,218],"their":[10,167,177],"acoustic":[11,27,67,125,165,204],"overlap,":[12],"which":[13],"has":[14],"led":[15],"interest":[17],"in":[18,58,104,145],"transferring":[19],"knowledge":[20,193],"between":[21,29,69,127,206],"these":[22],"domains.":[23],"However,":[24],"the":[25,45,66,79,124,140,203,213],"shared":[26,164],"cues":[28],"music,":[32,73,210],"particularly":[33],"those":[34],"encoded":[35],"by":[36,100,191],"Self-Supervised":[37],"Learning":[38],"(SSL)":[39],"models,":[40],"remain":[41],"largely":[42],"unexplored,":[43],"given":[44],"fact":[46],"that":[47,155],"SSL":[48,83,150,160],"models":[49,84,161],"for":[50,85,115,119,136,215],"have":[54],"rarely":[55],"been":[56],"applied":[57],"cross-domain":[59,98,216],"research.":[60],"In":[61],"this":[62],"work,":[63],"we":[64,96,122],"revisit":[65],"similarity":[68,205],"emotion":[70,143],"starting":[74],"with":[75],"an":[76],"analysis":[77],"of":[78,82,142],"layerwise":[80],"behavior":[81],"Speech":[86],"Recognition":[88,93],"(SER)":[89],"Music":[91],"(MER).":[94],"Furthermore,":[95],"perform":[97],"adaptation":[99],"comparing":[101],"several":[102],"approaches":[103],"a":[105],"two-stage":[106],"fine-tuning":[107,184],"process,":[108],"examining":[109],"effective":[110],"ways":[111],"utilize":[113],"SER":[116,187,220],"MER.":[120],"Lastly,":[121],"explore":[123],"emotional":[128,207],"using":[132],"Fr\u00e9chet":[133],"audio":[134],"distance":[135],"individual":[137],"emotions,":[138],"uncovering":[139],"issue":[141],"bias":[144],"both":[146],"models.":[151],"Our":[152],"findings":[153],"reveal":[154],"while":[156],"do":[162],"capture":[163],"features,":[166],"behaviors":[168],"can":[169,185],"vary":[170],"depending":[171],"on":[172],"different":[173],"emotions":[174],"training":[178],"strategies":[179],"domain-specificities.":[181],"Additionally,":[182],"parameter-efficient":[183],"enhance":[186],"MER":[189,222],"performance":[190],"leveraging":[192],"each":[195],"other.":[196],"This":[197],"study":[198],"provides":[199],"new":[200],"insights":[201],"into":[202],"highlights":[212],"potential":[214],"generalization":[217],"improve":[219],"systems.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}