{"id":"https://openalex.org/W3162293017","doi":"https://doi.org/10.1109/icassp39728.2021.9413659","title":"Improving Pronunciation Assessment Via Ordinal Regression with Anchored Reference Samples","display_name":"Improving Pronunciation Assessment Via Ordinal Regression with Anchored Reference Samples","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162293017","doi":"https://doi.org/10.1109/icassp39728.2021.9413659","mag":"3162293017"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5070490649","display_name":"Bin Su","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Bin Su","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies, and Systems, Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies, and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies, and Systems, Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies, and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"middle","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":false,"raw_author_name":"Shaoguang Mao","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","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,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","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,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","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,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies, and Systems, Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies, and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies, and Systems, Shenzhen International Graduate School, Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies, and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5070490649"],"corresponding_institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.6798,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74982985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"24","issue":null,"first_page":"7748","last_page":"7752"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9955999851226807,"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/T11309","display_name":"Music and Audio Processing","score":0.9894999861717224,"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":0.757938027381897},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6899176239967346},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.614310622215271},{"id":"https://openalex.org/keywords/ordinal-regression","display_name":"Ordinal regression","score":0.5869626998901367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4955943822860718},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4952496588230133},{"id":"https://openalex.org/keywords/pearson-product-moment-correlation-coefficient","display_name":"Pearson product-moment correlation coefficient","score":0.49042341113090515},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4504092037677765},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3881151080131531},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3101978898048401},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21265536546707153},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12009057402610779}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757938027381897},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6899176239967346},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.614310622215271},{"id":"https://openalex.org/C110313322","wikidata":"https://www.wikidata.org/wiki/Q7100793","display_name":"Ordinal regression","level":2,"score":0.5869626998901367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4955943822860718},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4952496588230133},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.49042341113090515},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4504092037677765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3881151080131531},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3101978898048401},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21265536546707153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12009057402610779},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W334543181","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1973435495","https://openalex.org/W2009088607","https://openalex.org/W2071128523","https://openalex.org/W2091265237","https://openalex.org/W2091856355","https://openalex.org/W2125398996","https://openalex.org/W2133487567","https://openalex.org/W2139881679","https://openalex.org/W2163094209","https://openalex.org/W2171541062","https://openalex.org/W2190044943","https://openalex.org/W2408752745","https://openalex.org/W2440214111","https://openalex.org/W2480455979","https://openalex.org/W2552635739","https://openalex.org/W2740984590","https://openalex.org/W2935807810","https://openalex.org/W3030437843","https://openalex.org/W3060039189","https://openalex.org/W3096674206","https://openalex.org/W4302313152","https://openalex.org/W6611433636","https://openalex.org/W6631362777","https://openalex.org/W6685221346","https://openalex.org/W6713615836","https://openalex.org/W6771467084","https://openalex.org/W6890361730"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2529301793","https://openalex.org/W2350724007","https://openalex.org/W2384121599","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2038083449","https://openalex.org/W1998701884"],"abstract_inverted_index":{"Sentence":[0],"level":[1,142],"pronunciation":[2,14],"assessment":[3,68],"is":[4,113,129,138],"important":[5],"for":[6,48,64],"Computer":[7],"Assisted":[8],"Language":[9],"Learning":[10],"(CALL).":[11],"Traditional":[12],"speech":[13,30],"assessment,":[15],"based":[16],"on":[17,115],"the":[18,110,132],"Goodness":[19],"of":[20,123,127],"Pronunciation":[21],"(GOP)":[22],"algorithm,":[23],"has":[24,56],"some":[25],"weakness":[26],"in":[27,61,101],"assessing":[28],"a":[29,41,45,66,73,98,120,140],"utterance:":[31],"1)":[32],"Phoneme":[33],"GOP":[34,62,87,91],"scores":[35],"cannot":[36],"be":[37],"easily":[38],"translated":[39],"into":[40],"sentence":[42],"score":[43],"with":[44,72,104],"simple":[46],"average":[47,86],"effective":[49],"assessment;":[50],"2)":[51],"The":[52,136],"rank":[53],"ordering":[54],"information":[55],"not":[57],"been":[58],"well":[59,71],"exploited":[60],"scoring":[63],"delivering":[65],"robust":[67],"and":[69,89,93],"correlate":[70],"human":[74,146],"rater\u2019s":[75],"evaluations.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80],"propose":[81],"two":[82],"new":[83],"statistical":[84],"features,":[85],"(aGOP)":[88],"confusion":[90],"(cGOP)":[92],"use":[94],"them":[95],"to":[96],"train":[97],"binary":[99],"classifier":[100],"Ordinal":[102],"Regression":[103],"Anchored":[105],"Reference":[106],"Samples":[107],"(ORARS).":[108],"When":[109],"proposed":[111],"approach":[112],"tested":[114],"Microsoft":[116],"mTutor":[117],"ESL":[118],"Dataset,":[119],"relative":[121],"improvement":[122],"Pearson":[124],"correlation":[125],"coefficient":[126],"26.9%":[128],"obtained":[130],"over":[131],"conventional":[133],"GOP-based":[134],"one.":[135],"performance":[137],"at":[139],"human-parity":[141],"or":[143],"better":[144],"than":[145],"raters.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}