{"id":"https://openalex.org/W4414069553","doi":"https://doi.org/10.3390/sym17091478","title":"Phoneme-Aware Augmentation for Robust Cantonese ASR Under Low-Resource Conditions","display_name":"Phoneme-Aware Augmentation for Robust Cantonese ASR Under Low-Resource Conditions","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W4414069553","doi":"https://doi.org/10.3390/sym17091478"},"language":"en","primary_location":{"id":"doi:10.3390/sym17091478","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym17091478","pdf_url":"https://www.mdpi.com/2073-8994/17/9/1478/pdf?version=1757303372","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/17/9/1478/pdf?version=1757303372","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010873419","display_name":"Lusheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I18452120","display_name":"Yantai University","ror":"https://ror.org/01rp41m56","country_code":"CN","type":"education","lineage":["https://openalex.org/I18452120"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lusheng Zhang","raw_affiliation_strings":["School of Physics and Electronic Information, Yantai University, Yantai 264005, China","Shandong Data Open Innovation Application Laboratory of Smart Grid Advanced Technology, Yantai University, Yantai 264005, China"],"affiliations":[{"raw_affiliation_string":"School of Physics and Electronic Information, Yantai University, Yantai 264005, China","institution_ids":["https://openalex.org/I18452120"]},{"raw_affiliation_string":"Shandong Data Open Innovation Application Laboratory of Smart Grid Advanced Technology, Yantai University, Yantai 264005, China","institution_ids":["https://openalex.org/I18452120"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086322265","display_name":"Shie Wu","orcid":"https://orcid.org/0000-0001-8264-0682"},"institutions":[{"id":"https://openalex.org/I18452120","display_name":"Yantai University","ror":"https://ror.org/01rp41m56","country_code":"CN","type":"education","lineage":["https://openalex.org/I18452120"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shie Wu","raw_affiliation_strings":["School of Physics and Electronic Information, Yantai University, Yantai 264005, China","Shandong Data Open Innovation Application Laboratory of Smart Grid Advanced Technology, Yantai University, Yantai 264005, China"],"affiliations":[{"raw_affiliation_string":"School of Physics and Electronic Information, Yantai University, Yantai 264005, China","institution_ids":["https://openalex.org/I18452120"]},{"raw_affiliation_string":"Shandong Data Open Innovation Application Laboratory of Smart Grid Advanced Technology, Yantai University, Yantai 264005, China","institution_ids":["https://openalex.org/I18452120"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087997118","display_name":"Zhongxun Wang","orcid":"https://orcid.org/0000-0001-6219-4515"},"institutions":[{"id":"https://openalex.org/I18452120","display_name":"Yantai University","ror":"https://ror.org/01rp41m56","country_code":"CN","type":"education","lineage":["https://openalex.org/I18452120"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhongxun Wang","raw_affiliation_strings":["School of Physics and Electronic Information, Yantai University, Yantai 264005, China","Shandong Data Open Innovation Application Laboratory of Smart Grid Advanced Technology, Yantai University, Yantai 264005, China"],"affiliations":[{"raw_affiliation_string":"School of Physics and Electronic Information, Yantai University, Yantai 264005, China","institution_ids":["https://openalex.org/I18452120"]},{"raw_affiliation_string":"Shandong Data Open Innovation Application Laboratory of Smart Grid Advanced Technology, Yantai University, Yantai 264005, China","institution_ids":["https://openalex.org/I18452120"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087997118"],"corresponding_institution_ids":["https://openalex.org/I18452120"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":5.0294,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95425907,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"17","issue":"9","first_page":"1478","last_page":"1478"},"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":0.9997000098228455,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.6579999923706055},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5076000094413757},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.5034000277519226},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.4726000130176544},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43290001153945923},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3862000107765198},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36309999227523804},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.3370000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692999839782715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7164999842643738},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.6579999923706055},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5076000094413757},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.5034000277519226},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43290001153945923},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3781999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3702999949455261},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2533000111579895},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/sym17091478","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym17091478","pdf_url":"https://www.mdpi.com/2073-8994/17/9/1478/pdf?version=1757303372","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/sym17091478","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym17091478","pdf_url":"https://www.mdpi.com/2073-8994/17/9/1478/pdf?version=1757303372","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5952885438","display_name":null,"funder_award_id":"62201491","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8947058724","display_name":null,"funder_award_id":"ZR2021QF097","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320308724","display_name":"Texas Space Grant Consortium","ror":"https://ror.org/05k1jx057"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414069553.pdf","grobid_xml":"https://content.openalex.org/works/W4414069553.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2747874407","https://openalex.org/W2936774411","https://openalex.org/W2963194026","https://openalex.org/W3036601975","https://openalex.org/W3198694222","https://openalex.org/W3209059054","https://openalex.org/W4295308567","https://openalex.org/W4296068827","https://openalex.org/W4322714819","https://openalex.org/W4372270126","https://openalex.org/W4385799550","https://openalex.org/W4385822337","https://openalex.org/W4385822995","https://openalex.org/W4385823436","https://openalex.org/W4392903704","https://openalex.org/W4408358622"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Cantonese":[0,140,200],"automatic":[1],"speech":[2,164],"recognition":[3],"(ASR)":[4],"faces":[5],"persistent":[6],"challenges":[7],"due":[8],"to":[9,59,158,167,182],"its":[10],"nine":[11],"lexical":[12],"tones,":[13],"extensive":[14],"phonological":[15],"variation,":[16],"and":[17,32,70,83,89,97,116,127,165,194],"the":[18,102,139,173,176],"scarcity":[19],"of":[20,142,163,175],"professionally":[21],"transcribed":[22],"corpora.":[23],"To":[24],"address":[25],"these":[26],"issues,":[27],"we":[28],"propose":[29],"a":[30,60,106,117,124],"lightweight":[31],"data-efficient":[33],"framework":[34],"that":[35,187],"leverages":[36],"weak":[37],"phonetic":[38,119],"supervision":[39],"(WPS)":[40],"in":[41],"conjunction":[42],"with":[43,160,169],"two":[44,177],"pho-neme-aware":[45],"augmentation":[46],"strategies.":[47],"(1)":[48],"Dynamic":[49,148],"Boundary-Aligned":[50],"Phoneme":[51],"Dropout":[52,149],"progressively":[53],"removes":[54],"entire":[55],"IPA":[56],"segments":[57],"according":[58],"curriculum":[61],"schedule,":[62],"simulating":[63],"real-world":[64],"phenomena":[65],"such":[66],"as":[67],"elision,":[68],"lenition,":[69],"tonal":[71],"drift":[72],"while":[73,172],"ensuring":[74],"training":[75],"stability.":[76],"(2)":[77],"Phoneme-Aware":[78],"SpecAugment":[79],"confines":[80],"all":[81],"time-":[82],"frequency-masking":[84],"operations":[85],"within":[86],"phoneme":[87,152],"boundaries":[88],"prioritizes":[90],"high-attention":[91],"regions,":[92],"thereby":[93],"preserving":[94],"intra-phonemic":[95],"contours":[96],"formant":[98],"integrity.":[99],"Built":[100],"on":[101,138],"Whistle":[103],"encoder\u2014which":[104],"integrates":[105],"Conformer":[107],"backbone,":[108],"Connectionist":[109],"Temporal":[110],"Classification\u2013Conditional":[111],"Random":[112],"Field":[113],"(CTC-CRF)":[114],"alignment,":[115],"multi-lingual":[118],"space\u2014the":[120],"approach":[121],"requires":[122],"only":[123],"grapheme-to-phoneme":[125],"lexicon":[126],"Montreal":[128],"Forced":[129],"Aligner":[130],"outputs,":[131],"without":[132],"any":[133],"additional":[134],"manual":[135],"labeling.":[136],"Experiments":[137],"subset":[141],"Common":[143],"Voice":[144],"demonstrate":[145],"consistent":[146],"gains:":[147],"alone":[150],"reduces":[151],"error":[153],"rate":[154],"(PER)":[155],"from":[156],"17.8%":[157],"16.7%":[159],"50":[161],"h":[162],"16.4%":[166],"15.1%":[168],"100":[170],"h,":[171],"combination":[174],"augmentations":[178],"further":[179],"lowers":[180],"PER":[181],"15.9%/14.4%.":[183],"These":[184],"results":[185],"confirm":[186],"structure-aware":[188],"phoneme-level":[189],"perturbations":[190],"provide":[191],"an":[192],"effective":[193],"low-cost":[195],"solution":[196],"for":[197],"building":[198],"robust":[199],"ASR":[201],"systems":[202],"under":[203],"low-resource":[204],"conditions.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
