{"id":"https://openalex.org/W4224920457","doi":"https://doi.org/10.1109/icassp43922.2022.9747774","title":"A Universal Ordinal Regression for Assessing Phoneme-Level Pronunciation","display_name":"A Universal Ordinal Regression for Assessing Phoneme-Level Pronunciation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920457","doi":"https://doi.org/10.1109/icassp43922.2022.9747774"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747774","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":"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/A5052035563","display_name":"Shaoguang Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaoguang Mao","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank Soong","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101917127","display_name":"Yan Xia","orcid":"https://orcid.org/0000-0003-3843-6275"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Xia","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084928812","display_name":"Jonathan Tien","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jonathan Tien","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052035563"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.37292609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6807","last_page":"6811"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9965999722480774,"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":0.9950000047683716,"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/ordinal-regression","display_name":"Ordinal regression","score":0.7377820014953613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7130865454673767},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6662811040878296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4964502453804016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4699687361717224},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.4613499641418457},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.44388431310653687},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35479605197906494},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16888493299484253},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15469399094581604},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08982503414154053}],"concepts":[{"id":"https://openalex.org/C110313322","wikidata":"https://www.wikidata.org/wiki/Q7100793","display_name":"Ordinal regression","level":2,"score":0.7377820014953613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7130865454673767},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6662811040878296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4964502453804016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4699687361717224},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.4613499641418457},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.44388431310653687},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35479605197906494},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16888493299484253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15469399094581604},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08982503414154053},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747774","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":0.7699999809265137,"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":32,"referenced_works":["https://openalex.org/W290344559","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1585763212","https://openalex.org/W1931766939","https://openalex.org/W2023389730","https://openalex.org/W2091856355","https://openalex.org/W2164810574","https://openalex.org/W2185463204","https://openalex.org/W2370418772","https://openalex.org/W2400818677","https://openalex.org/W2408752745","https://openalex.org/W2440214111","https://openalex.org/W2552635739","https://openalex.org/W2740984590","https://openalex.org/W2889562042","https://openalex.org/W2890962360","https://openalex.org/W2935807810","https://openalex.org/W3015231007","https://openalex.org/W3096674206","https://openalex.org/W3156081754","https://openalex.org/W3160255128","https://openalex.org/W3162293017","https://openalex.org/W3197742413","https://openalex.org/W4293518005","https://openalex.org/W6629717138","https://openalex.org/W6631362777","https://openalex.org/W6635132915","https://openalex.org/W6656299101","https://openalex.org/W6718478815","https://openalex.org/W6794778313","https://openalex.org/W6800613197"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W2359469050","https://openalex.org/W1607396156"],"abstract_inverted_index":{"The":[0],"efficacy":[1],"and":[2,57,81,169],"robustness":[3],"of":[4,38,74,107,120,157,163],"Ordinal":[5,69],"Regression":[6,70],"(OR)":[7],"in":[8,91,124],"assessing":[9,24],"speech":[10,148],"pronunciation":[11,151],"for":[12,23,35,50,78,150],"language":[13],"learning":[14],"at":[15],"phrase":[16],"level":[17],"has":[18],"been":[19],"shown":[20],"before.":[21],"However,":[22],"phoneme":[25,36,52,113,122,132],"pronunciation,":[26],"we":[27,63,153],"need":[28],"to:":[29],"1.":[30],"collect":[31],"human":[32],"scoring":[33],"annotations":[34],"tokens":[37,109,119],"a":[39,67,97,105,146],"short":[40],"duration":[41],"(60-70":[42],"ms);":[43],"2.":[44],"train":[45,66],"an":[46],"ordinal":[47],"regression":[48],"model":[49,72],"each":[51],"with":[53,110,130],"the":[54,111,125,141,155,158,180],"corresponding":[55],"training":[56,126],"inference":[58],"costs.":[59],"In":[60,115],"this":[61],"paper,":[62],"propose":[64],"to":[65,95,134],"Universal":[68],"(UOR)":[71],"instead":[73],"multiple,":[75],"separate":[76],"models":[77],"different":[79],"phonemes,":[80],"evaluate":[82],"its":[83],"performance":[84],"accordingly.":[85],"A":[86],"single":[87],"universal":[88],"binary":[89,98,136],"classifier":[90],"UOR":[92,143],"is":[93],"trained":[94],"make":[96,135],"preference":[99,137],"decision":[100],"(better":[101],"or":[102],"worse)":[103],"between":[104],"pair":[106],"two":[108],"same":[112],"ID.":[114],"inference,":[116],"labeled":[117],"anchored":[118],"specific":[121],"ID":[123],"data":[127],"are":[128,177],"paired":[129],"test":[131],"token":[133],"decisions.":[138],"By":[139],"evaluating":[140],"new":[142,160],"on":[144],"Speechocean762,":[145],"public":[147],"database":[149],"evaluation,":[152],"show":[154],"advantages":[156],"proposed":[159],"approach.":[161],"Improvements":[162],"Pearson":[164],"Correlation":[165],"Coefficient":[166],"by":[167,173],"16.7%":[168],"Mean":[170],"Square":[171],"Error":[172],"25.0%,":[174],"all":[175],"relatively,":[176],"obtained":[178],"against":[179],"state-of-the-art":[181],"systems.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}