{"id":"https://openalex.org/W4392931003","doi":"https://doi.org/10.1109/icassp48485.2024.10447225","title":"Multi-Dimensional Speech Quality Assessment in Crowdsourcing","display_name":"Multi-Dimensional Speech Quality Assessment in Crowdsourcing","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931003","doi":"https://doi.org/10.1109/icassp48485.2024.10447225"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5069905492","display_name":"Babak Naderi","orcid":"https://orcid.org/0009-0006-4778-5417"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Babak Naderi","raw_affiliation_strings":["Microsoft Corporation,Redmond,USA","Microsoft Corporation, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068040769","display_name":"Ross Cutler","orcid":"https://orcid.org/0000-0002-2004-3003"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ross Cutler","raw_affiliation_strings":["Microsoft Corporation,Redmond,USA","Microsoft Corporation, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083932459","display_name":"Nicolae-C\u0103t\u0103lin Ristea","orcid":"https://orcid.org/0000-0002-7880-9307"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicolae-C\u0103t\u0103lin Ristea","raw_affiliation_strings":["Microsoft Corporation,Redmond,USA","Microsoft Corporation, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069905492"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":5.2505,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.9630046,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"696","last_page":"700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9959999918937683,"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"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.8381080031394958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7519341707229614},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6218569278717041},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6200402975082397},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5371018648147583},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.426783949136734},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4262089431285858},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.41678786277770996},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4113796353340149},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.12398451566696167},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07958412170410156},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07551982998847961}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.8381080031394958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519341707229614},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6218569278717041},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6200402975082397},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5371018648147583},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.426783949136734},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4262089431285858},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.41678786277770996},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4113796353340149},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.12398451566696167},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07958412170410156},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07551982998847961},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W39714443","https://openalex.org/W1552314771","https://openalex.org/W2103934944","https://openalex.org/W2395622121","https://openalex.org/W2407595713","https://openalex.org/W2486436843","https://openalex.org/W2626626553","https://openalex.org/W2734477997","https://openalex.org/W2799449427","https://openalex.org/W2922332774","https://openalex.org/W3015717277","https://openalex.org/W3018201762","https://openalex.org/W3025844872","https://openalex.org/W3100211355","https://openalex.org/W3101528112","https://openalex.org/W3107070581","https://openalex.org/W3161480375","https://openalex.org/W3195288392","https://openalex.org/W3196475561","https://openalex.org/W4221144124","https://openalex.org/W4225302959","https://openalex.org/W4401610398","https://openalex.org/W6675521023","https://openalex.org/W6850335419"],"related_works":["https://openalex.org/W1546240199","https://openalex.org/W193702574","https://openalex.org/W2063862874","https://openalex.org/W2154415461","https://openalex.org/W1923241916","https://openalex.org/W2151365363","https://openalex.org/W2798852438","https://openalex.org/W642007152","https://openalex.org/W254504168","https://openalex.org/W1967664370"],"abstract_inverted_index":{"Subjective":[0],"speech":[1,10,27,50,66,110,144],"quality":[2,28,48,67,145],"assessment":[3],"is":[4,119],"the":[5,47,52,60,73,77,99,109,117,130,140],"gold":[6],"standard":[7,19],"for":[8,38],"evaluating":[9],"enhancement":[11],"processing":[12],"and":[13,32,63,86,103,112,122,137],"telecommunication":[14],"systems.":[15],"The":[16,79,124,150],"commonly":[17],"used":[18,128],"ITU-T":[20,33,40,56],"Rec.":[21,34,41,57],"P.800":[22,44],"defines":[23],"how":[24],"to":[25,45,106],"measure":[26,46],"in":[29,51,129,147],"lab":[30],"environments,":[31],"P.808":[35],"extended":[36],"it":[37,105],"crowdsourcing.":[39],"P.835":[42],"extends":[43],"of":[49,54,76,93,142],"presence":[53],"noise.":[55],"P.804":[58,102],"targets":[59],"conversation":[61],"test":[62,97],"introduces":[64],"perceptual":[65,80],"dimensions":[68,81,146],"which":[69],"are":[70,82],"measured":[71],"during":[72],"listening":[74],"phase":[75],"conversation.":[78],"noisiness,":[83],"coloration,":[84],"discontinuity,":[85],"loudness.":[87],"We":[88,115],"create":[89],"a":[90,94],"crowd-sourcing":[91],"implementation":[92],"multi-dimensional":[95],"subjective":[96],"following":[98],"scales":[100],"from":[101],"extend":[104],"include":[107],"reverberation,":[108],"signal,":[111],"overall":[113],"quality.":[114],"show":[116,139],"tool":[118,125,151],"both":[120],"accurate":[121],"reproducible.":[123],"has":[126],"been":[127],"ICASSP":[131],"2023":[132],"Speech":[133],"Signal":[134],"Improvement":[135],"challenge":[136],"we":[138],"utility":[141],"these":[143],"this":[148],"challenge.":[149],"will":[152],"be":[153],"publicly":[154],"available":[155],"as":[156],"open-source":[157],"at":[158],"https://github.com/microsoft/P.808.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
