{"id":"https://openalex.org/W4406461704","doi":"https://doi.org/10.1109/slt61566.2024.10832269","title":"Enhancing Automatic Speech Assessment Leveraging Heterogeneous Features and Soft Labels For Ordinal Classification","display_name":"Enhancing Automatic Speech Assessment Leveraging Heterogeneous Features and Soft Labels For Ordinal Classification","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461704","doi":"https://doi.org/10.1109/slt61566.2024.10832269"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5102725500","display_name":"Wei\u2010Qi Peng","orcid":"https://orcid.org/0009-0004-4709-4566"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Wen-Hsuan Peng","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035748246","display_name":"Sally Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122797","display_name":"Electronics Testing Center","ror":"https://ror.org/034rqbg02","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I4210122797"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sally Chen","raw_affiliation_strings":["The Language Training & Testing Center"],"affiliations":[{"raw_affiliation_string":"The Language Training & Testing Center","institution_ids":["https://openalex.org/I4210122797"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047673862","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102725500"],"corresponding_institution_ids":["https://openalex.org/I134161618"],"apc_list":null,"apc_paid":null,"fwci":0.6891,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77768791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"945","last_page":"952"},"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":0.9987999796867371,"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":0.9958999752998352,"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":0.7940317392349243},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5557816028594971},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5134233236312866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4554154872894287},{"id":"https://openalex.org/keywords/ordinal-regression","display_name":"Ordinal regression","score":0.4321581721305847},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39794665575027466},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2981604337692261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940317392349243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5557816028594971},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5134233236312866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4554154872894287},{"id":"https://openalex.org/C110313322","wikidata":"https://www.wikidata.org/wiki/Q7100793","display_name":"Ordinal regression","level":2,"score":0.4321581721305847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39794665575027466},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2981604337692261}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":22,"referenced_works":["https://openalex.org/W66698146","https://openalex.org/W1979364015","https://openalex.org/W2069029003","https://openalex.org/W2395066838","https://openalex.org/W2803039862","https://openalex.org/W2912981563","https://openalex.org/W2939437245","https://openalex.org/W2949208911","https://openalex.org/W2964051877","https://openalex.org/W2979826702","https://openalex.org/W3036691700","https://openalex.org/W3140560950","https://openalex.org/W4223651314","https://openalex.org/W4311000453","https://openalex.org/W4312120823","https://openalex.org/W4319586625","https://openalex.org/W4319862401","https://openalex.org/W4363675386","https://openalex.org/W4385573574","https://openalex.org/W4385822293","https://openalex.org/W4391021508","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W3210452439","https://openalex.org/W2912776266","https://openalex.org/W3048012572","https://openalex.org/W66181126","https://openalex.org/W4399574212","https://openalex.org/W89855045","https://openalex.org/W1539030525","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,128],"general":[1],"goal":[2],"of":[3,21,47,55,78,83,89,98,138,145,154],"automated":[4],"speech":[5],"assessment":[6],"(ASA)":[7],"is":[8,130],"to":[9,29,66,124],"provide":[10],"a":[11,37,108],"consistent":[12],"and":[13,41,94,152],"objective":[14],"evaluation":[15],"on":[16],"the":[17,44,53,76,87,96,116,135,149],"spoken":[18],"language":[19],"proficiency":[20,48],"an":[22],"L2":[23],"learner":[24],"or":[25],"test-taker.":[26],"In":[27,62],"contrast":[28],"most":[30],"previous":[31],"work":[32],"that":[33,115],"treats":[34],"ASA":[35,68],"as":[36],"nominal":[38],"multi-classification":[39],"task":[40],"thus":[42],"neglects":[43],"sequential":[45],"nature":[46],"grades,":[49],"this":[50],"paper":[51],"explores":[52],"notion":[54],"soft":[56,80],"labels":[57,81,85],"for":[58,92],"use":[59],"in":[60,86,134,143],"ASA.":[61],"particular,":[63],"we":[64],"strive":[65],"enhance":[67,121],"performance":[69,122],"by":[70],"examining":[71],"two":[72],"critical":[73],"issues:":[74],"(1)":[75],"impact":[77],"applying":[79],"instead":[82],"hard":[84],"optimization":[88],"ordinal":[90],"classification":[91],"ASA,":[93],"(2)":[95],"effects":[97],"combining":[99],"self-supervised":[100],"learning":[101],"(SSL)":[102],"with":[103],"handcrafted":[104],"indicator":[105],"features":[106],"via":[107],"novel":[109],"modeling":[110],"paradigm.":[111],"Our":[112],"results":[113],"demonstrate":[114],"proposed":[117],"model":[118],"can":[119],"considerably":[120],"compared":[123],"existing":[125],"strong":[126],"baselines.":[127],"improvement":[129],"evident":[131],"not":[132],"only":[133],"test":[136],"dataset":[137],"seen":[139],"prompts":[140],"but":[141],"also":[142],"those":[144],"unseen":[146],"prompts,":[147],"suggesting":[148],"robust":[150],"generalization":[151],"adaptability":[153],"our":[155],"method.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}