{"id":"W2813631418","doi":"10.21437/interspeech.2018-2293","title":"Tone Recognition Using Lifters and CTC","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Speech recognition; Computer science; Tone (literature); Mandarin Chinese; Word error rate; Connectionism; Convolutional neural network; Sequence (biology); Artificial intelligence; Artificial neural network; Mel-frequency cepstrum; Cepstrum; Pattern recognition (psychology); Feature extraction","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004049692,0.0006841088,0.0005227166,0.001012124,0.0003170535,0.0006619879,0.0006621782,0.0006483958,0.003484485],"category_scores_gemma":[0.001476735,0.0002497392,0.0003787525,0.000570179,0.0003374512,0.0009219302,0.0008783679,0.0008840741,0.001987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002327625,"about_ca_system_score_gemma":0.0004038303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003095672,"about_ca_topic_score_gemma":0.004571255,"domain_scores_codex":[0.9994368,0.0000675018,0.00002876478,0.0001923105,0.0002106138,0.00006399651],"domain_scores_gemma":[0.9993929,0.0001915911,0.00004188082,0.0001447614,0.0001915778,0.00003726495],"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":[0.0003617867,0.00009692911,0.001732926,0.0001125259,0.00004630167,0.0004520423,0.00008152992,0.01296594,0.1607658,0.00325604,0.003392122,0.816736],"study_design_scores_gemma":[0.00004246546,0.000222434,0.004984775,0.00002739132,0.00006618203,0.0009897938,0.00007443949,0.8607894,0.1165645,0.003428827,0.01275717,0.00005261197],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1126455,0.0009978183,0.8693634,0.0002019176,0.0004548823,0.0001747269,0.0004906286,0.00660757,0.009063622],"genre_scores_gemma":[0.6533257,0.0005300411,0.3286816,0.0002360354,0.0002242399,0.0001187151,0.001856222,0.0003107278,0.01471675],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003484485,"threshold_uncertainty_score":0.01165676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06160652313651099,"score_gpt":0.3108954982292729,"score_spread":0.2492889750927619,"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."}}