{"id":"W4414069553","doi":"10.3390/sym17091478","title":"Phoneme-Aware Augmentation for Robust Cantonese ASR Under Low-Resource Conditions","year":2025,"lang":"en","type":"article","venue":"Symmetry","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; Natural Science Foundation of Shandong Province; Texas Space Grant Consortium","keywords":"Dropout (neural networks); Connectionism; Formant; Lexicon; Word error rate; Field (mathematics); Speech processing; Conjunction (astronomy)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016387,0.0001126817,0.0001299509,0.000248534,0.0002343961,0.0001295116,0.0003368167,0.00007216763,0.0001493446],"category_scores_gemma":[0.0000739977,0.0001125908,0.00009577638,0.0005735813,0.00003621919,0.0002128552,0.00006870812,0.00007191278,0.00009143943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008810178,"about_ca_system_score_gemma":0.00009922739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004329624,"about_ca_topic_score_gemma":0.0000519391,"domain_scores_codex":[0.9990873,0.00004934915,0.0001907307,0.0003015845,0.0001575769,0.0002134521],"domain_scores_gemma":[0.9991612,0.0003049473,0.00005815558,0.0003058065,0.0001031779,0.00006669308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005677731,0.0007380258,0.001208819,0.0003504778,0.0003954485,0.00002219717,0.0006477591,0.0006337108,0.006217552,0.3120987,0.3027941,0.3748364],"study_design_scores_gemma":[0.01023477,0.000308675,0.04271175,0.001016517,0.0003661031,0.00007357859,0.008650389,0.3901144,0.3105689,0.1396734,0.09357435,0.002707197],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01018671,0.00005650822,0.9716948,0.003325564,0.0006023977,0.0003324022,0.00005794027,0.0002144808,0.01352923],"genre_scores_gemma":[0.9188188,0.00001525434,0.06289272,0.007959648,0.0001446337,0.0002717975,0.0001632356,0.0000232873,0.009710629],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.908802,"threshold_uncertainty_score":0.4591318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02059244963797242,"score_gpt":0.2863763270053069,"score_spread":0.2657838773673344,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}