{"id":"https://openalex.org/W4406745078","doi":"https://doi.org/10.1109/icassp49660.2025.10888929","title":"Investigating the Sensitivity of Pre-trained Audio Embeddings to Common Effects","display_name":"Investigating the Sensitivity of Pre-trained Audio Embeddings to Common Effects","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4406745078","doi":"https://doi.org/10.1109/icassp49660.2025.10888929"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888929","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.15900","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069358194","display_name":"Victor Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Victor Deng","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris,France","ENS-PSL - \u00c9cole normale sup\u00e9rieure - Paris (45, Rue d'Ulm - 75230 Paris cedex 05 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]},{"raw_affiliation_string":"ENS-PSL - \u00c9cole normale sup\u00e9rieure - Paris (45, Rue d'Ulm - 75230 Paris cedex 05 - France)","institution_ids":["https://openalex.org/I29607241"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427137","display_name":"Changhong Wang","orcid":"https://orcid.org/0000-0001-9955-0851"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Changhong Wang","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris,France","LTCI - Laboratoire Traitement et Communication de l'Information (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 PALAISEAU - France)","S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]},{"raw_affiliation_string":"LTCI - Laboratoire Traitement et Communication de l'Information (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 PALAISEAU - France)","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]},{"raw_affiliation_string":"S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ga\u00ebl Richard","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris,France","IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","LTCI - Laboratoire Traitement et Communication de l'Information (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 PALAISEAU - France)","S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I4210145102"]},{"raw_affiliation_string":"IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","institution_ids":[]},{"raw_affiliation_string":"LTCI - Laboratoire Traitement et Communication de l'Information (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 PALAISEAU - France)","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]},{"raw_affiliation_string":"S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","institution_ids":["https://openalex.org/I12356871"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010404092","display_name":"Brian McFee","orcid":"https://orcid.org/0000-0001-6261-9747"},"institutions":[{"id":"https://openalex.org/I4210089335","display_name":"Perfect Harmony Health","ror":"https://ror.org/00835yh61","country_code":"US","type":"other","lineage":["https://openalex.org/I4210089335"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian McFee","raw_affiliation_strings":["New York University,Music and Audio Research Laboratory,USA","NYU - New York University [New York] (70 Washington Square South, New York, NY 10012 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Music and Audio Research Laboratory,USA","institution_ids":["https://openalex.org/I4210089335","https://openalex.org/I57206974"]},{"raw_affiliation_string":"NYU - New York University [New York] (70 Washington Square South, New York, NY 10012 - United States)","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069358194"],"corresponding_institution_ids":["https://openalex.org/I29607241","https://openalex.org/I4210145102","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":2.212,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.84615385,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9769999980926514,"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/computer-science","display_name":"Computer science","score":0.6939772963523865},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6452327370643616},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5496663451194763},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5444773435592651},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.48867538571357727},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.470449835062027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47035837173461914},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4240318238735199},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3427524268627167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.338584840297699},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1173490583896637},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11124813556671143}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6939772963523865},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6452327370643616},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5496663451194763},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5444773435592651},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.48867538571357727},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.470449835062027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47035837173461914},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4240318238735199},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3427524268627167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.338584840297699},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1173490583896637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11124813556671143},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888929","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"},{"id":"pmh:oai:arXiv.org:2501.15900","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.15900","pdf_url":"https://arxiv.org/pdf/2501.15900","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"},{"id":"pmh:oai:HAL:hal-04904470v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04904470","pdf_url":"https://hal.science/hal-04904470v1/file/main.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Apr 2025, Hyderabad, India","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.15900","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.15900","pdf_url":"https://arxiv.org/pdf/2501.15900","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":[{"id":"https://openalex.org/G4326088756","display_name":null,"funder_award_id":"101052978","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406745078.pdf","grobid_xml":"https://content.openalex.org/works/W4406745078.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2889326414","https://openalex.org/W3003257820","https://openalex.org/W3094550259","https://openalex.org/W4206297453","https://openalex.org/W4249992252","https://openalex.org/W4312938053","https://openalex.org/W4372266552","https://openalex.org/W4383899470","https://openalex.org/W4392903801","https://openalex.org/W6635274319","https://openalex.org/W6766336120","https://openalex.org/W6791537541","https://openalex.org/W6855234272"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W4255576661","https://openalex.org/W1516574938","https://openalex.org/W2625725254","https://openalex.org/W2563912921"],"abstract_inverted_index":{"In":[0,25],"recent":[1],"years,":[2],"foundation":[3,41],"models":[4],"have":[5],"significantly":[6],"advanced":[7],"data-driven":[8],"systems":[9],"across":[10],"various":[11],"domains.":[12],"Yet,":[13],"their":[14,60],"underlying":[15],"properties,":[16],"especially":[17],"when":[18],"functioning":[19],"as":[20,53,127],"feature":[21],"extractors,":[22],"remain":[23],"under-explored.":[24],"this":[26],"paper,":[27],"we":[28,78],"investigate":[29],"the":[30,54,80,83,87,91,98,103,123,128,135,138,153,167,174],"sensitivity":[31,57],"to":[32,59,96,179],"audio":[33,36,51,65,70,108,129,147,180],"effects":[34,52,71,109],"of":[35,56,102,176],"embeddings":[37,124,148,178],"extracted":[38],"from":[39],"widely-used":[40],"models,":[42],"including":[43],"OpenL3,":[44],"PANNs,":[45],"and":[46,76,86,100],"CLAP.":[47],"We":[48,94,114],"focus":[49],"on":[50,158],"source":[55],"due":[58],"prevalent":[61],"presence":[62],"in":[63,90],"large":[64],"datasets.":[66],"By":[67],"applying":[68],"parameterized":[69],"(gain,":[72],"low-pass":[73],"filtering,":[74],"reverberation,":[75],"bitcrushing),":[77],"analyze":[79],"correlation":[81,112],"between":[82],"deformation":[84,104,169],"trajectories":[85,105],"effect":[88,130],"strength":[89,131],"embedding":[92],"space.":[93],"propose":[95],"quantify":[97],"dimensionality":[99],"linearizability":[101],"induced":[106],"by":[107],"using":[110],"canonical":[111],"analysis.":[113],"find":[115],"that":[116,134,145,164],"there":[117],"exists":[118],"a":[119],"direction":[120],"along":[121],"which":[122],"move":[125],"monotonically":[126],"increases,":[132],"but":[133],"subspace":[136],"containing":[137],"displacements":[139],"is":[140],"generally":[141,172],"high-dimensional.":[142],"This":[143],"shows":[144],"pre-trained":[146,177],"do":[149],"not":[150],"globally":[151],"linearize":[152],"effects.":[154,181],"Our":[155],"empirical":[156],"results":[157],"instrument":[159],"classification":[160],"downstream":[161],"tasks":[162],"confirm":[163],"projecting":[165],"out":[166],"estimated":[168],"directions":[170],"cannot":[171],"improve":[173],"robustness":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-02T09:04:35.204637","created_date":"2025-10-10T00:00:00"}
