{"id":"https://openalex.org/W4385822603","doi":"https://doi.org/10.21437/interspeech.2023-1679","title":"Score-balanced Loss for Multi-aspect Pronunciation Assessment","display_name":"Score-balanced Loss for Multi-aspect Pronunciation Assessment","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822603","doi":"https://doi.org/10.21437/interspeech.2023-1679"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1679","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1679","pdf_url":"https://www.isca-archive.org/interspeech_2023/do23b_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2023/do23b_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007104233","display_name":"Heejin Do","orcid":"https://orcid.org/0000-0001-7320-415X"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Heejin Do","raw_affiliation_strings":["Graduate School of AI, POSTECH, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of AI, POSTECH, Republic of Korea","institution_ids":["https://openalex.org/I2799891827","https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090577558","display_name":"Yunsu Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yunsu Kim","raw_affiliation_strings":["Graduate School of AI, POSTECH, Republic of Korea","Department of Computer Science and Engineering, POSTECH, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of AI, POSTECH, Republic of Korea","institution_ids":["https://openalex.org/I2799891827","https://openalex.org/I123900574"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, POSTECH, Republic of Korea","institution_ids":["https://openalex.org/I2799891827","https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024406631","display_name":"Gary Geunbae Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gary Geunbae Lee","raw_affiliation_strings":["Graduate School of AI, POSTECH, Republic of Korea","Department of Computer Science and Engineering, POSTECH, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of AI, POSTECH, Republic of Korea","institution_ids":["https://openalex.org/I2799891827","https://openalex.org/I123900574"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, POSTECH, Republic of Korea","institution_ids":["https://openalex.org/I2799891827","https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007104233"],"corresponding_institution_ids":["https://openalex.org/I123900574","https://openalex.org/I2799891827"],"apc_list":null,"apc_paid":null,"fwci":0.5247,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71612963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4998","last_page":"5002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9986000061035156,"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":0.9973000288009644,"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/pronunciation","display_name":"Pronunciation","score":0.8657100796699524},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.856139063835144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7142674922943115},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.6262534260749817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49294424057006836},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4906820058822632},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4835962653160095},{"id":"https://openalex.org/keywords/score","display_name":"Score","score":0.42971378564834595},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3291120231151581},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3278402090072632},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15008428692817688},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11750736832618713},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.06988206505775452}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8657100796699524},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.856139063835144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7142674922943115},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.6262534260749817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49294424057006836},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4906820058822632},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4835962653160095},{"id":"https://openalex.org/C65660741","wikidata":"https://www.wikidata.org/wiki/Q3952743","display_name":"Score","level":2,"score":0.42971378564834595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3291120231151581},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3278402090072632},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15008428692817688},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11750736832618713},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.06988206505775452},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1679","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1679","pdf_url":"https://www.isca-archive.org/interspeech_2023/do23b_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2023-1679","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1679","pdf_url":"https://www.isca-archive.org/interspeech_2023/do23b_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1739134435","display_name":null,"funder_award_id":"IITP-","funder_id":"https://openalex.org/F4320324891","funder_display_name":"Iran Telecommunication Research Center"},{"id":"https://openalex.org/G1903519916","display_name":null,"funder_award_id":"2019-0-01906","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2702555917","display_name":null,"funder_award_id":"2019-0-01906","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6072120315","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6153356302","display_name":null,"funder_award_id":"IITP-2023-2020-0-01789","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G6946461118","display_name":null,"funder_award_id":"2019-0-01906","funder_id":"https://openalex.org/F4320321282","funder_display_name":"Pohang University of Science and Technology"},{"id":"https://openalex.org/G743292859","display_name":null,"funder_award_id":"IITP-2023-2020-0-01789","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8036681666","display_name":null,"funder_award_id":"2019-0-01906","funder_id":"https://openalex.org/F4320324891","funder_display_name":"Iran Telecommunication Research Center"},{"id":"https://openalex.org/G8516825431","display_name":null,"funder_award_id":"No. 2019-0-01906","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320321282","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385822603.pdf","grobid_xml":"https://content.openalex.org/works/W4385822603.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1941659294","https://openalex.org/W1967624650","https://openalex.org/W1988687075","https://openalex.org/W2016114400","https://openalex.org/W2023639956","https://openalex.org/W2039568842","https://openalex.org/W2118978333","https://openalex.org/W2139008940","https://openalex.org/W2148143831","https://openalex.org/W2164810574","https://openalex.org/W2167642311","https://openalex.org/W2559844874","https://openalex.org/W2963691377","https://openalex.org/W2980748755","https://openalex.org/W3096674206","https://openalex.org/W3132250316","https://openalex.org/W3146641898","https://openalex.org/W4224928163","https://openalex.org/W4224932147","https://openalex.org/W4287241492","https://openalex.org/W4312069033","https://openalex.org/W4312901050","https://openalex.org/W4372262414","https://openalex.org/W4385245566"],"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/W2180954594","https://openalex.org/W4220683390","https://openalex.org/W2365169615","https://openalex.org/W2776838583"],"abstract_inverted_index":{"With":[0],"rapid":[1],"technological":[2],"growth,":[3],"automatic":[4],"pronunciation":[5,13],"assessment":[6],"has":[7,122],"transitioned":[8],"toward":[9,61],"systems":[10],"that":[11],"evaluate":[12,114],"in":[14],"various":[15],"aspects,":[16],"such":[17,58,132],"as":[18,59],"fluency":[19],"and":[20,108],"stress.However,":[21],"despite":[22],"the":[23,36,52,62,73,78,83,100,110,118,136],"highly":[24],"imbalanced":[25,124],"score":[26,75,91],"labels":[27],"within":[28],"each":[29],"aspect,":[30],"existing":[31],"studies":[32],"have":[33],"rarely":[34],"tackled":[35],"data":[37],"imbalance":[38],"problem.In":[39],"this":[40],"paper,":[41],"we":[42,68,93],"suggest":[43],"a":[44,65],"novel":[45],"loss":[46],"function,":[47],"score-balanced":[48],"loss,":[49],"to":[50,85],"address":[51],"problem":[53],"caused":[54],"by":[55,98],"uneven":[56,133],"data,":[57],"bias":[60],"majority":[63],"scores.As":[64],"re-weighting":[66],"approach,":[67],"assign":[69],"higher":[70],"costs":[71],"when":[72],"predicted":[74],"is":[76],"of":[77,102,106,112,138],"minority":[79],"class,":[80],"thus,":[81],"guiding":[82],"model":[84],"gain":[86],"positive":[87],"feedback":[88],"for":[89,126],"sparse":[90],"prediction.Specifically,":[92],"design":[94],"two":[95],"weighting":[96],"factors":[97],"leveraging":[99],"concept":[101],"an":[103],"effective":[104],"number":[105],"samples":[107],"using":[109],"ranks":[111],"scores.We":[113],"our":[115,139],"method":[116],"on":[117,131],"speechocean762":[119],"dataset,":[120],"which":[121],"noticeably":[123],"scores":[125],"several":[127],"aspects.Improved":[128],"results":[129],"particularly":[130],"aspects":[134],"prove":[135],"effectiveness":[137],"method.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}
