{"id":"W2940842789","doi":"10.1121/1.5101632","title":"Automated Mandarin tone classification using deep neural networks trained on a large speech dataset","year":2019,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Music and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Mandarin Chinese; Computer science; Tone (literature); Speech recognition; Intonation (linguistics); Mel-frequency cepstrum; Pitch contour; Convolutional neural network; Artificial intelligence; Artificial neural network; Cepstrum; Pattern recognition (psychology); Feature extraction; Linguistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009772726,0.001211572,0.0005448205,0.001196534,0.0005897698,0.0007032554,0.000780822,0.0007271376,0.001864924],"category_scores_gemma":[0.002063393,0.0002503552,0.0005977947,0.000724524,0.0002944705,0.0006472416,0.0008523275,0.0009078139,0.001602789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006592209,"about_ca_system_score_gemma":0.000623124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009764764,"about_ca_topic_score_gemma":0.0181842,"domain_scores_codex":[0.99941,0.0001161612,0.00004869165,0.0002565851,0.00009195815,0.00007657729],"domain_scores_gemma":[0.9990415,0.0003867004,0.00005204539,0.0001914018,0.0002747253,0.00005354622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001303001,0.001131463,0.02099487,0.0004223418,0.0002615544,0.0009081794,0.0005140726,0.05543442,0.1210798,0.001033795,0.02378941,0.773127],"study_design_scores_gemma":[0.00009009433,0.0004524129,0.03434698,0.00004505736,0.00009668734,0.0002854935,0.0004428863,0.8991392,0.05461084,0.001385854,0.009039533,0.00006494253],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9091162,0.001287582,0.06662018,0.0003274635,0.0003238179,0.0002557145,0.008600823,0.006548342,0.006919888],"genre_scores_gemma":[0.846314,0.0003089523,0.1046326,0.000163083,0.00008423119,0.0003155567,0.04073337,0.0001950025,0.007253266],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009764764,"threshold_uncertainty_score":0.01941586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02263625642710846,"score_gpt":0.2941247880298188,"score_spread":0.2714885316027103,"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."}}