{"id":"https://openalex.org/W4406461824","doi":"https://doi.org/10.1109/slt61566.2024.10832138","title":"Semi-Supervised Learning for Robust Speech Evaluation","display_name":"Semi-Supervised Learning for Robust Speech Evaluation","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461824","doi":"https://doi.org/10.1109/slt61566.2024.10832138"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832138","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/A5102856166","display_name":"Huayun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Huayun Zhang","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR) 1 Fusionopolis Way, Connexis #21-01,Singapore,138632"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR) 1 Fusionopolis Way, Connexis #21-01,Singapore,138632","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048201022","display_name":"Jeremy H. M. Wong","orcid":"https://orcid.org/0000-0003-3742-7510"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jeremy H.M. Wong","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR) 1 Fusionopolis Way, Connexis #21-01,Singapore,138632"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR) 1 Fusionopolis Way, Connexis #21-01,Singapore,138632","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101339717","display_name":"Geyu Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Geyu Lin","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR) 1 Fusionopolis Way, Connexis #21-01,Singapore,138632"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR) 1 Fusionopolis Way, Connexis #21-01,Singapore,138632","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014190404","display_name":"Nancy F. Chen","orcid":"https://orcid.org/0000-0003-0872-5877"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nancy F. Chen","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR) 1 Fusionopolis Way, Connexis #21-01,Singapore,138632"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR) 1 Fusionopolis Way, Connexis #21-01,Singapore,138632","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102856166"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2384718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"991","last_page":"998"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.9932000041007996,"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":0.760348916053772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5805206298828125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4636026620864868},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3545432984828949}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760348916053772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5805206298828125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4636026620864868},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3545432984828949}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832138","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1995875735","https://openalex.org/W2039568842","https://openalex.org/W2091856355","https://openalex.org/W2118978333","https://openalex.org/W2139008940","https://openalex.org/W2164810574","https://openalex.org/W2292087804","https://openalex.org/W2402146185","https://openalex.org/W2514528237","https://openalex.org/W2514741789","https://openalex.org/W2575763737","https://openalex.org/W2768707988","https://openalex.org/W2768986418","https://openalex.org/W2889080286","https://openalex.org/W2921829459","https://openalex.org/W2979826702","https://openalex.org/W2995181338","https://openalex.org/W3036601975","https://openalex.org/W3095355634","https://openalex.org/W3095410713","https://openalex.org/W3096174632","https://openalex.org/W3096270392","https://openalex.org/W3096582851","https://openalex.org/W3096674206","https://openalex.org/W3119308075","https://openalex.org/W3148504935","https://openalex.org/W3196891430","https://openalex.org/W3197742413","https://openalex.org/W3198694222","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224928163","https://openalex.org/W4226148503","https://openalex.org/W4297841616","https://openalex.org/W4312069033","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6804000844","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Speech":[0],"evaluation":[1,82,146],"measures":[2],"a":[3,158,174],"learner\u2019s":[4],"oral":[5],"proficiency":[6,36,187],"using":[7,107],"automatic":[8],"models.":[9],"Corpora":[10],"for":[11],"training":[12],"such":[13,70],"models":[14],"often":[15,22,39],"pose":[16],"sparsity":[17],"challenges":[18,71],"given":[19],"that":[20],"there":[21],"is":[23,46,89,105,120],"limited":[24],"scored":[25],"data":[26,198],"from":[27,96],"teachers,":[28],"in":[29,61],"addition":[30],"to":[31,68,79,91,110,122,131,153],"the":[32,93,97,100,112,126,136,144,149,170,179,193],"score":[33],"distribution":[34],"across":[35,185],"levels":[37],"being":[38],"imbalanced":[40],"among":[41],"student":[42],"cohorts.":[43],"Automatic":[44],"scoring":[45],"thus":[47],"not":[48,124,163],"robust":[49],"when":[50],"faced":[51],"with":[52,129,202],"under-represented":[53],"samples":[54],"or":[55],"out-of-distribution":[56,197],"samples,":[57],"which":[58],"inevitably":[59],"exist":[60],"real-world":[62],"deployment":[63],"scenarios.":[64],"This":[65],"paper":[66],"proposes":[67],"address":[69],"by":[72,143],"exploiting":[73],"semi-supervised":[74],"pre-training":[75],"and":[76,99,148],"objective":[77],"regularization":[78],"approximate":[80],"subjective":[81],"criteria.":[83],"In":[84],"particular,":[85],"normalized":[86],"mutual":[87],"information":[88],"used":[90],"quantify":[92],"speech":[94,145],"characteristics":[95],"learner":[98],"reference.":[101],"An":[102,116],"anchor":[103,150],"model":[104,147,194],"trained":[106],"pseudo":[108],"labels":[109],"predict":[111],"correctness":[113],"of":[114],"pronunciation.":[115],"interpolated":[117],"loss":[118],"function":[119],"proposed":[121],"minimize":[123],"only":[125,164],"prediction":[127,183],"error":[128,184],"respect":[130],"ground-truth":[132],"scores":[133],"but":[134,176],"also":[135,177,199],"divergence":[137],"between":[138],"two":[139],"probability":[140],"distributions":[141],"estimated":[142],"model.":[151],"Compared":[152],"other":[154],"state-of-the-art":[155],"methods":[156],"on":[157,196],"public":[159],"data-set,":[160],"this":[161],"approach":[162],"achieves":[165],"high":[166],"performance":[167],"while":[168],"evaluating":[169],"entire":[171],"test-set":[172],"as":[173],"whole,":[175],"brings":[178],"most":[180],"evenly":[181],"distributed":[182],"distinct":[186],"levels.":[188],"Furthermore,":[189],"empirical":[190],"results":[191],"show":[192],"accuracy":[195],"compares":[200],"favorably":[201],"competitive":[203],"baselines.":[204]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}