{"id":"https://openalex.org/W4296068605","doi":"https://doi.org/10.21437/interspeech.2022-406","title":"SAQAM: Spatial Audio Quality Assessment Metric","display_name":"SAQAM: Spatial Audio Quality Assessment Metric","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068605","doi":"https://doi.org/10.21437/interspeech.2022-406"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-406","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-406","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":"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/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, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101853595","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0003-2984-5325"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Meta Reality Labs Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Meta Reality Labs Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059034612","display_name":"Anjali Kondur Menon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anjali Menon","raw_affiliation_strings":["Meta Reality Labs Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076456660","display_name":"Israel Degene Gebru","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Israel Degene Gebru","raw_affiliation_strings":["Meta Reality Labs Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108520440","display_name":"Vamsi Krishna Ithapu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vamsi Krishna Ithapu","raw_affiliation_strings":["Meta Reality Labs Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004601228","display_name":"Paul Calamia","orcid":"https://orcid.org/0000-0002-0401-6996"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Calamia","raw_affiliation_strings":["Meta Reality Labs Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2104,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8152345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"649","last_page":"653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9962999820709229,"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":0.7810865640640259},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.669776439666748},{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.523216724395752},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4601479470729828},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42608392238616943},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.27497950196266174},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07888033986091614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7810865640640259},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.669776439666748},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.523216724395752},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4601479470729828},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42608392238616943},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27497950196266174},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07888033986091614},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-406","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-406","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":35,"referenced_works":["https://openalex.org/W1481240155","https://openalex.org/W1493897031","https://openalex.org/W1494198834","https://openalex.org/W1515109179","https://openalex.org/W1520657064","https://openalex.org/W1552314771","https://openalex.org/W1561928502","https://openalex.org/W1842577739","https://openalex.org/W1975517671","https://openalex.org/W2009649672","https://openalex.org/W2025401819","https://openalex.org/W2097117768","https://openalex.org/W2136682440","https://openalex.org/W2143156057","https://openalex.org/W2284050935","https://openalex.org/W2398217754","https://openalex.org/W2516342150","https://openalex.org/W2549440896","https://openalex.org/W2606611007","https://openalex.org/W2768337397","https://openalex.org/W2948105160","https://openalex.org/W2948208658","https://openalex.org/W2948364140","https://openalex.org/W2953163324","https://openalex.org/W2961183107","https://openalex.org/W2963775347","https://openalex.org/W2985229398","https://openalex.org/W2991361823","https://openalex.org/W3002439978","https://openalex.org/W3023239811","https://openalex.org/W3097934054","https://openalex.org/W3129121609","https://openalex.org/W3200245256","https://openalex.org/W3211188239","https://openalex.org/W4205225513"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2149396112","https://openalex.org/W1572216403","https://openalex.org/W2622965534","https://openalex.org/W1963988314","https://openalex.org/W1924500548"],"abstract_inverted_index":{"Audio":[0],"quality":[1,32,61,65],"assessment":[2],"is":[3,119,125],"critical":[4],"for":[5,100,134],"assessing":[6],"the":[7,12,23,39,47,123],"perceptual":[8],"realism":[9],"of":[10,16,25,35,46,71,87,102],"sounds.However,":[11],"time":[13],"and":[14,33,63,91],"expense":[15],"obtaining":[17],"\"gold":[18],"standard\"":[19],"human":[20,89,112],"judgments":[21],"limit":[22],"availability":[24],"such":[26],"data.For":[27],"AR&VR,":[28],"good":[29],"perceived":[30],"sound":[31],"localizability":[34],"sources":[36],"are":[37],"among":[38],"key":[40],"elements":[41],"to":[42,58],"ensure":[43],"complete":[44],"immersion":[45],"user.Our":[48],"work":[49],"introduces":[50],"SAQAM":[51,108],"which":[52],"uses":[53],"a":[54,84,120,131,149],"multi-task":[55],"learning":[56],"framework":[57],"assess":[59],"listening":[60],"(LQ)":[62],"spatialization":[64],"(SQ)":[66],"between":[67],"any":[68,76],"given":[69],"pair":[70],"binaural":[72],"signals":[73],"without":[74],"using":[75],"subjective":[77],"data.We":[78],"model":[79],"LQ":[80],"by":[81,93],"training":[82],"on":[83],"simulated":[85],"dataset":[86],"triplet":[88],"judgments,":[90],"SQ":[92],"utilizing":[94],"activation-level":[95],"distances":[96],"from":[97],"networks":[98],"trained":[99],"direction":[101],"arrival":[103],"(DOA)":[104],"estimation.We":[105],"show":[106],"that":[107],"correlates":[109],"well":[110],"with":[111,143],"responses":[113],"across":[114],"four":[115],"diverse":[116],"datasets.Since":[117],"it":[118,128],"deep":[121],"network,":[122],"metric":[124,145],"differentiable,":[126],"making":[127],"suitable":[129],"as":[130],"loss":[132,142],"function":[133],"other":[135],"tasks.For":[136],"example,":[137],"simply":[138],"replacing":[139],"an":[140],"existing":[141],"our":[144],"yields":[146],"improvement":[147],"in":[148],"speech-enhancement":[150],"network.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}