{"id":"https://openalex.org/W4297841868","doi":"https://doi.org/10.21437/interspeech.2022-405","title":"Audio Similarity is Unreliable as a Proxy for Audio Quality","display_name":"Audio Similarity is Unreliable as a Proxy for Audio Quality","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841868","doi":"https://doi.org/10.21437/interspeech.2022-405"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-405","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-405","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","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/A5075510192","display_name":"Pranay Manocha","orcid":"https://orcid.org/0000-0003-3284-5908"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pranay Manocha","raw_affiliation_strings":["Department of Computer Science, Princeton University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034842939","display_name":"Adam Finkelstein","orcid":"https://orcid.org/0000-0001-9422-5363"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Finkelstein","raw_affiliation_strings":["Department of Computer Science, Princeton University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3553","last_page":"3557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9455000162124634,"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":0.9455000162124634,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7376220226287842},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.653294563293457},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4440653622150421},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.42928194999694824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3017290234565735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2259298861026764},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08819171786308289}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376220226287842},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.653294563293457},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4440653622150421},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42928194999694824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3017290234565735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2259298861026764},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08819171786308289},{"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:10.21437/interspeech.2022-405","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-405","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1728888090","https://openalex.org/W2067295501","https://openalex.org/W2086381917","https://openalex.org/W2103934944","https://openalex.org/W2111964411","https://openalex.org/W2141044085","https://openalex.org/W2166153901","https://openalex.org/W2408467190","https://openalex.org/W2557915412","https://openalex.org/W2757519008","https://openalex.org/W2809874909","https://openalex.org/W2949558265","https://openalex.org/W2972394484","https://openalex.org/W2987307811","https://openalex.org/W3044096495","https://openalex.org/W3049430014","https://openalex.org/W3096159803","https://openalex.org/W3097627357","https://openalex.org/W3097934054","https://openalex.org/W3097945073","https://openalex.org/W3160506022","https://openalex.org/W3161364427","https://openalex.org/W3196475561","https://openalex.org/W3200245256","https://openalex.org/W3202278141","https://openalex.org/W4224920010","https://openalex.org/W4297841519","https://openalex.org/W4311167834","https://openalex.org/W4361745739"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W2296317756"],"abstract_inverted_index":{"Many":[0],"audio":[1,133],"processing":[2],"tasks":[3],"require":[4],"perceptual":[5],"assessment.However,":[6],"the":[7,18],"time":[8],"and":[9,45,95,117],"expense":[10],"of":[11,20],"obtaining":[12],"\"gold":[13],"standard\"":[14],"human":[15,75,121],"judgments":[16],"limit":[17],"availability":[19],"such":[21,41,115],"data.Most":[22],"applications":[23],"incorporate":[24],"full":[25],"reference":[26],"or":[27],"other":[28],"similarity-based":[29],"metrics":[30,42,70,110],"(e.g.PESQ)":[31],"that":[32,52,88,108,125],"depend":[33],"on":[34,40,86],"a":[35],"clean":[36,82],"reference.Researchers":[37],"have":[38],"relied":[39],"to":[43,72,99],"evaluate":[44],"compare":[46],"various":[47],"proposed":[48],"methods,":[49],"often":[50],"concluding":[51],"small,":[53],"measured":[54],"differences":[55],"imply":[56],"one":[57],"is":[58],"more":[59],"effective":[60],"than":[61],"another.This":[62],"paper":[63],"demonstrates":[64],"several":[65],"practical":[66],"scenarios":[67],"where":[68],"similarity":[69,126],"fail":[71],"agree":[73],"with":[74,81,120],"perception,":[76],"because":[77],"they:":[78],"(1)":[79],"vary":[80],"references;":[83],"(2)":[84],"rely":[85],"attributes":[87],"humans":[89],"factor":[90],"out":[91],"when":[92],"considering":[93],"quality,":[94],"(3)":[96],"are":[97],"sensitive":[98],"imperceptible":[100],"signal":[101],"level":[102],"differences.In":[103],"those":[104],"scenarios,":[105],"we":[106],"show":[107],"no-reference":[109],"do":[111],"not":[112],"suffer":[113],"from":[114],"shortcomings":[116],"correlate":[118],"better":[119],"perception.We":[122],"conclude":[123],"therefore":[124],"serves":[127],"as":[128],"an":[129],"unreliable":[130],"proxy":[131],"for":[132],"quality.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}