{"id":"W1993505392","doi":"10.1121/1.4779035","title":"A human vocal utterance corpus for perceptual and acoustic analysis of speech, singing, and intermediate vocalizations","year":2002,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Music and Audio Processing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Utterance; Singing; Annotation; Computer science; Speech recognition; Speech corpus; Perception; Natural language processing; Artificial intelligence; Speech synthesis; Acoustics; Psychology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000339975,0.0000988965,0.0003475595,0.00004260972,0.0002320629,0.00003906843,0.00051235,0.00003804067,0.00001525606],"category_scores_gemma":[0.0001375146,0.0000564518,0.0002347781,0.0004864672,0.000873873,0.0001253158,0.0001905137,0.0001712535,1.229817e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001738139,"about_ca_system_score_gemma":0.00002034972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009612885,"about_ca_topic_score_gemma":8.313024e-7,"domain_scores_codex":[0.9990159,0.00006387557,0.0003830018,0.0001057784,0.0002710538,0.0001603487],"domain_scores_gemma":[0.9986942,0.0003788663,0.0005010414,0.0001967963,0.0001644129,0.00006470329],"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":[0.0001051976,0.0007519323,0.003662773,0.0007121373,0.004007655,0.00000539152,0.06960605,0.09572501,0.1634196,0.0002854954,0.0384456,0.6232731],"study_design_scores_gemma":[0.0002706457,0.0001717645,0.003274699,0.00007605197,0.0008926076,0.0000285529,0.0005855389,0.9937377,0.0002202193,0.0005140414,0.0001533889,0.00007477523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08830322,0.0003336103,0.9090549,0.002157084,0.0000596882,0.00006036626,0.000005395782,0.00000556293,0.00002011122],"genre_scores_gemma":[0.9512243,0.0001808284,0.0472493,0.001222668,0.00007228029,5.233846e-7,1.54876e-7,0.000005509568,0.00004441374],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8980127,"threshold_uncertainty_score":0.3219822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01779515894985953,"score_gpt":0.2589692334632795,"score_spread":0.24117407451342,"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."}}