{"id":"W4412633897","doi":"10.1121/10.0037229","title":"Non-native listener perceptual similarity ratings as a measure of L2 speech production","year":2025,"lang":"en","type":"article","venue":"JASA Express Letters","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Pierre Elliott Trudeau Foundation","keywords":"Pronunciation; German; First language; Similarity (geometry); Linguistics; Psychology; Perception; Computer science; Speech recognition; Natural language processing; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000468895,0.000170802,0.0002855457,0.0002081186,0.0001203772,0.00002288097,0.0003482499,0.0001933764,0.0005711917],"category_scores_gemma":[0.0002132384,0.0001621679,0.0001028994,0.0003167783,0.0003634625,0.00007190948,0.0001251245,0.0005357209,0.00007550035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004723451,"about_ca_system_score_gemma":0.00005766945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009361151,"about_ca_topic_score_gemma":0.00003234771,"domain_scores_codex":[0.9983231,0.0002452047,0.0002919839,0.0005015828,0.0002807897,0.0003572669],"domain_scores_gemma":[0.9989681,0.0001230464,0.0001060126,0.0005515941,0.0001948831,0.00005642269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003756761,0.000266255,0.006691642,0.00005702475,0.0002310404,0.00003036581,0.02348882,0.00003091359,0.7866082,0.0002838859,0.1792928,0.002643465],"study_design_scores_gemma":[0.003935826,0.0005402153,0.4509723,0.0003544717,0.0001732524,0.00005666847,0.00850292,0.0001789223,0.509336,0.001757449,0.02328179,0.000910204],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9722797,0.0000847778,0.0002886636,0.009705965,0.001042807,0.0004205685,0.00001571594,0.00003517334,0.01612668],"genre_scores_gemma":[0.9914123,0.000006510563,0.0003740356,0.002360425,0.0001968205,0.00009250787,0.00001344889,0.0000176491,0.005526336],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4442807,"threshold_uncertainty_score":0.6613014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02504892687024627,"score_gpt":0.3371041322229477,"score_spread":0.3120552053527014,"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."}}