{"id":"https://openalex.org/W4401609030","doi":"https://doi.org/10.1109/icasspw62465.2024.10627629","title":"Layer-Wise Analysis of Self-Supervised Acoustic Word Embeddings: A Study on Speech Emotion Recognition","display_name":"Layer-Wise Analysis of Self-Supervised Acoustic Word Embeddings: A Study on Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609030","doi":"https://doi.org/10.1109/icasspw62465.2024.10627629"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10627629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10627629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5069463899","display_name":"Alexandra Saliba","orcid":null},"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":"Alexandra Saliba","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077749078","display_name":"Yuanchao Li","orcid":"https://orcid.org/0000-0002-8005-947X"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053704856","display_name":"Ramon Sanabria","orcid":null},"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":"Ramon Sanabria","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058881584","display_name":"Catherine Lai","orcid":"https://orcid.org/0000-0003-2411-8954"},"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":"Catherine Lai","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3601,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93180243,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"590","last_page":"594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8034999966621399,"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":0.8034999966621399,"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":0.7473605275154114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7324466705322266},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5857818722724915},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5808020830154419},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5314406752586365},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5278846025466919},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4610956907272339},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21663013100624084}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7473605275154114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7324466705322266},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5857818722724915},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5808020830154419},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5314406752586365},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5278846025466919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4610956907272339},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21663013100624084},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10627629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10627629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2004409624","https://openalex.org/W2059652594","https://openalex.org/W2097207027","https://openalex.org/W2126203737","https://openalex.org/W2146334809","https://openalex.org/W2747874407","https://openalex.org/W2995755016","https://openalex.org/W3036601975","https://openalex.org/W3110761489","https://openalex.org/W3164582967","https://openalex.org/W3197580070","https://openalex.org/W3198429080","https://openalex.org/W3209059054","https://openalex.org/W4205742757","https://openalex.org/W4225635674","https://openalex.org/W4226380987","https://openalex.org/W4319862479","https://openalex.org/W4319862652","https://openalex.org/W4375869060","https://openalex.org/W4375869259","https://openalex.org/W4378464659","https://openalex.org/W4385485018","https://openalex.org/W6780218876","https://openalex.org/W6786885278","https://openalex.org/W6852678209"],"related_works":["https://openalex.org/W1569283511","https://openalex.org/W4236193183","https://openalex.org/W2053866214","https://openalex.org/W2607505004","https://openalex.org/W2231795205","https://openalex.org/W2523632547","https://openalex.org/W2143882141","https://openalex.org/W2296205523","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"The":[0],"efficacy":[1],"of":[2,13,56,82,89,95,131],"self-supervised":[3,123],"speech":[4,90],"models":[5],"has":[6],"been":[7],"validated,":[8],"yet":[9],"the":[10,72,80,93,128,143,151],"optimal":[11],"utilization":[12,130],"their":[14,40],"representations":[15],"remains":[16],"challenging":[17],"across":[18],"diverse":[19],"tasks.":[20,44],"In":[21,54],"this":[22],"study,":[23],"we":[24,58,78,116],"delve":[25],"into":[26],"Acoustic":[27],"Word":[28],"Embeddings":[29],"(AWEs),":[30],"a":[31,101,105],"fixed-length":[32],"feature":[33],"derived":[34],"from":[35],"continuous":[36],"representations,":[37,124],"to":[38,69,86],"explore":[39,117],"advantages":[41],"in":[42,50,84,92,135],"specific":[43],"AWEs":[45,64,120,132,148],"have":[46],"previously":[47],"shown":[48],"utility":[49],"capturing":[51],"acoustic":[52,144],"discriminability.":[53],"light":[55],"this,":[57],"propose":[59],"measuring":[60],"layer-wise":[61,106],"similarity":[62],"between":[63,119],"and":[65,104,114,121,134,149],"word":[66,138],"embeddings,":[67],"aiming":[68],"further":[70],"investigate":[71],"inherent":[73],"context":[74,94,145],"within":[75],"AWEs.":[76,159],"Moreover,":[77],"evaluate":[79],"contribution":[81],"AWEs,":[83],"comparison":[85],"other":[87],"types":[88],"features,":[91],"Speech":[96],"Emotion":[97],"Recognition":[98],"(SER).":[99],"Through":[100],"comparative":[102],"experiment":[103],"accuracy":[107],"analysis":[108],"on":[109],"two":[110],"distinct":[111],"corpora,":[112],"IEMOCAP":[113],"ESD,":[115],"differences":[118],"raw":[122],"as":[125,127],"well":[126],"proper":[129],"alone":[133],"combination":[136],"with":[137],"embeddings.":[139],"Our":[140],"findings":[141],"underscore":[142],"conveyed":[146],"by":[147,156],"showcase":[150],"highly":[152],"competitive":[153],"SER":[154],"accuracies":[155],"appropriately":[157],"employing":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}