{"id":"https://openalex.org/W4224920010","doi":"https://doi.org/10.1109/icassp43922.2022.9746615","title":"SQAPP: No-Reference Speech Quality Assessment Via Pairwise Preference","display_name":"SQAPP: No-Reference Speech Quality Assessment Via Pairwise Preference","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920010","doi":"https://doi.org/10.1109/icassp43922.2022.9746615"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746615","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":["Princeton University,USA","Princeton University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University,USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"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","Adobe Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research,USA","institution_ids":["https://openalex.org/I1306409833"]},{"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":["Princeton University,USA","Princeton University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University,USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"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":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"891","last_page":"895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9983999729156494,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.8548423051834106},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7288963794708252},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6152583360671997},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6146657466888428},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5947898626327515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5832937359809875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4978659152984619},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.48245030641555786},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4616175591945648},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4548429250717163},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44065943360328674},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33134177327156067}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.8548423051834106},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7288963794708252},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6152583360671997},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6146657466888428},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5947898626327515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5832937359809875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4978659152984619},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.48245030641555786},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4616175591945648},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4548429250717163},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44065943360328674},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33134177327156067},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746615","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1275832873","https://openalex.org/W1552314771","https://openalex.org/W1594713653","https://openalex.org/W1728888090","https://openalex.org/W1755499802","https://openalex.org/W1795254317","https://openalex.org/W2033442452","https://openalex.org/W2035412504","https://openalex.org/W2097117768","https://openalex.org/W2105854852","https://openalex.org/W2105921478","https://openalex.org/W2140828385","https://openalex.org/W2473388484","https://openalex.org/W2737697117","https://openalex.org/W2757519008","https://openalex.org/W2792764867","https://openalex.org/W2809874909","https://openalex.org/W2890983311","https://openalex.org/W2922332774","https://openalex.org/W2940385941","https://openalex.org/W2948210185","https://openalex.org/W2963035245","https://openalex.org/W2963403924","https://openalex.org/W2987307811","https://openalex.org/W2990118552","https://openalex.org/W2998733532","https://openalex.org/W3002439978","https://openalex.org/W3015644200","https://openalex.org/W3096159803","https://openalex.org/W3097934054","https://openalex.org/W3097945073","https://openalex.org/W3160506022","https://openalex.org/W3161364427","https://openalex.org/W3161480375","https://openalex.org/W3196475561","https://openalex.org/W3197042120","https://openalex.org/W3198102247","https://openalex.org/W3200245256","https://openalex.org/W4200483526","https://openalex.org/W4205689591","https://openalex.org/W6635487435","https://openalex.org/W6637602730","https://openalex.org/W6720742747","https://openalex.org/W6749825310","https://openalex.org/W6772622344","https://openalex.org/W6783462664","https://openalex.org/W6785764544","https://openalex.org/W6801588699"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2562400057","https://openalex.org/W1692008701","https://openalex.org/W2597588799","https://openalex.org/W4360593462","https://openalex.org/W2194570607","https://openalex.org/W2807634898","https://openalex.org/W2894446834"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,196],"quality":[2,97,138,148],"assessment":[3],"remains":[4],"challenging,":[5],"as":[6,52,178],"we":[7,132,142,187],"lack":[8,53],"complete":[9],"models":[10,18],"of":[11,54,98,112],"human":[12,22,107,163],"auditory":[13],"perception.":[14],"Many":[15],"existing":[16,195],"full-reference":[17],"correlate":[19],"well":[20],"with":[21,85,162],"perception,":[23],"but":[24],"cannot":[25],"be":[26],"used":[27],"in":[28],"real-world":[29],"scenarios":[30],"where":[31],"ground":[32],"truth":[33],"clean":[34],"reference":[35],"recordings":[36,84],"are":[37],"not":[38],"available.":[39],"On":[40],"the":[41,73,96,144,156,171],"other":[42],"hand":[43],"no-reference":[44],"metrics":[45],"typically":[46],"suffer":[47],"from":[48],"several":[49],"shortcomings,":[50],"such":[51],"robustness":[55],"to":[56,78,146,193],"unseen":[57],"perturbations":[58],"and":[59,104,140],"reliance":[60],"on":[61,149],"(limited)":[62],"labeled":[63],"data":[64],"for":[65,83,94,182],"training.":[66],"Moreover,":[67],"noise":[68],"or":[69],"large":[70],"variance":[71],"among":[72],"labels":[74],"makes":[75],"it":[76,166,176],"difficult":[77],"learn":[79,134],"generalizable":[80],"representations,":[81],"especially":[82],"subtle":[86],"differences.":[87],"This":[88],"paper":[89],"proposes":[90],"a":[91,99,116,135,168,179],"learning":[92,126],"framework":[93,114],"estimating":[95],"recording":[100],"without":[101,105],"any":[102,106],"reference,":[103],"judgments.":[108,164],"The":[109],"main":[110],"component":[111],"this":[113,191],"is":[115,160,167,173],"pairwise":[117,130],"quality-preference":[118],"strategy":[119],"that":[120,155,189],"reduces":[121],"label":[122],"noise,":[123],"thereby":[124],"making":[125,175],"more":[127],"robust.":[128],"From":[129],"preferences,":[131],"first":[133],"content":[136],"invariant":[137],"ordering;":[139],"then":[141],"re-target":[143],"model":[145],"predict":[147],"an":[150,194],"absolute":[151],"scale.":[152],"We":[153],"show":[154,188],"resulting":[157],"learned":[158],"metric":[159,172,192],"well-calibrated":[161],"Since":[165],"deep":[169],"network,":[170],"differentiable,":[174],"suitable":[177],"loss":[180],"function":[181],"downstream":[183],"tasks.":[184],"For":[185],"example,":[186],"adding":[190],"enhancement":[197],"method":[198],"yields":[199],"significant":[200],"improvement.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}