{"id":"https://openalex.org/W4401597538","doi":"https://doi.org/10.1109/icasspw62465.2024.10625960","title":"Benchmarking Representations for Speech, Music, and Acoustic Events","display_name":"Benchmarking Representations for Speech, Music, and Acoustic Events","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401597538","doi":"https://doi.org/10.1109/icasspw62465.2024.10625960"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10625960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10625960","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/A5078641012","display_name":"Moreno La Quatra","orcid":"https://orcid.org/0000-0001-8838-064X"},"institutions":[{"id":"https://openalex.org/I246010334","display_name":"Universit\u00e0 degli Studi di Enna Kore","ror":"https://ror.org/04vd28p53","country_code":"IT","type":"education","lineage":["https://openalex.org/I246010334"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Moreno La Quatra","raw_affiliation_strings":["Kore University of Enna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kore University of Enna","institution_ids":["https://openalex.org/I246010334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083365850","display_name":"Alkis Koudounas","orcid":"https://orcid.org/0000-0003-4386-0409"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alkis Koudounas","raw_affiliation_strings":["Politecnico di Torino"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082357372","display_name":"Lorenzo Vaiani","orcid":"https://orcid.org/0000-0002-3605-1577"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Vaiani","raw_affiliation_strings":["Politecnico di Torino"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001695309","display_name":"Elena Baralis","orcid":"https://orcid.org/0000-0001-9231-467X"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elena Baralis","raw_affiliation_strings":["Politecnico di Torino"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001746215","display_name":"Luca Cagliero","orcid":"https://orcid.org/0000-0002-7185-5247"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Cagliero","raw_affiliation_strings":["Politecnico di Torino"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074057809","display_name":"Paolo Garza","orcid":"https://orcid.org/0000-0002-1263-7522"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Garza","raw_affiliation_strings":["Politecnico di Torino"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["Università Degli Studi di Palermo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Università Degli Studi di Palermo","institution_ids":["https://openalex.org/I900890020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1456,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88720084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"505","last_page":"509"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.48570001125335693,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.48570001125335693,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/benchmarking","display_name":"Benchmarking","score":0.8656402826309204},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6429208517074585},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6025965809822083},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3662031888961792},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.061937421560287476}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8656402826309204},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6429208517074585},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6025965809822083},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3662031888961792},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.061937421560287476},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10625960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10625960","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"},{"id":"pmh:oai:iris.unipa.it:10447/663738","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/663738","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"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":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W589698015","https://openalex.org/W1494198834","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2593116425","https://openalex.org/W2973157397","https://openalex.org/W2995181338","https://openalex.org/W3081192838","https://openalex.org/W3100460087","https://openalex.org/W3119308075","https://openalex.org/W3189296823","https://openalex.org/W3195486004","https://openalex.org/W3197580070","https://openalex.org/W3198694222","https://openalex.org/W3205475937","https://openalex.org/W3206996142","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4205689591","https://openalex.org/W4210836801","https://openalex.org/W4225713393","https://openalex.org/W4289821214","https://openalex.org/W4293370787","https://openalex.org/W4310873011","https://openalex.org/W4389619460","https://openalex.org/W6617505242","https://openalex.org/W6635274319","https://openalex.org/W6678969435","https://openalex.org/W6712692208","https://openalex.org/W6732646663","https://openalex.org/W6757817989","https://openalex.org/W6780218876","https://openalex.org/W6798597329","https://openalex.org/W6809947431","https://openalex.org/W6810007534","https://openalex.org/W6843775035"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687"],"abstract_inverted_index":{"Limited":[0],"diversity":[1],"in":[2],"standardized":[3],"benchmarks":[4],"for":[5,26,92],"evaluating":[6,27],"audio":[7,32],"representation":[8],"learning":[9],"(ARL)":[10],"methods":[11,29],"may":[12],"hinder":[13],"systematic":[14],"comparison":[15],"of":[16,54,60,71,88],"current":[17,86],"methods\u2019":[18],"capabilities.":[19],"We":[20,108],"present":[21],"ARCH,":[22],"a":[23,68],"comprehensive":[24],"benchmark":[25],"ARL":[28,61,120],"on":[30,105],"diverse":[31],"classification":[33],"domains,":[34],"covering":[35],"acoustic":[36],"events,":[37],"music,":[38],"and":[39,73,81,122],"speech.":[40],"ARCH":[41,57],"comprises":[42],"12":[43],"datasets,":[44],"that":[45,101,110],"allow":[46],"us":[47],"to":[48,67,76,125],"thoroughly":[49],"assess":[50],"pre-trained":[51,90,99],"SSL":[52],"models":[53,91,100],"different":[55],"sizes.":[56],"streamlines":[58],"benchmarking":[59],"techniques":[62],"through":[63],"its":[64,74],"unified":[65],"access":[66],"wide":[69],"range":[70],"domains":[72],"ability":[75],"readily":[77],"incorporate":[78],"new":[79,98],"datasets":[80],"models.":[82],"To":[83],"address":[84],"the":[85,111],"lack":[87],"open-source,":[89],"non-speech":[93,106],"audio,":[94],"we":[95],"also":[96],"release":[97],"demonstrate":[102],"strong":[103],"performance":[104],"datasets.":[107],"argue":[109],"presented":[112],"wide-ranging":[113],"evaluation":[114],"provides":[115],"valuable":[116],"insights":[117],"into":[118],"state-of-the-art":[119],"methods,":[121],"is":[123],"useful":[124],"pinpoint":[126],"promising":[127],"research":[128],"directions.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7}],"updated_date":"2026-06-25T08:15:23.626066","created_date":"2025-10-10T00:00:00"}