{"id":"W3081192838","doi":"10.5281/zenodo.1188976","title":"The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS)","year":2018,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":329,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Audio visual; Computer science; Speech recognition; Database; Communication; Psychology; Multimedia","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001607807,0.0002304446,0.0002623393,0.0002994946,0.002225008,0.0003983494,0.001615656,0.0002471441,0.03241781],"category_scores_gemma":[0.0007298237,0.0001991412,0.00006163107,0.0004121955,0.001153158,0.00007949617,0.002290262,0.0008007608,0.007458954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006465995,"about_ca_system_score_gemma":0.00001374947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001931102,"about_ca_topic_score_gemma":0.000007292686,"domain_scores_codex":[0.997053,0.0008568897,0.0003735728,0.0006130459,0.0005429189,0.0005605262],"domain_scores_gemma":[0.997784,0.0001588734,0.000237488,0.0009730855,0.0006461864,0.0002003367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002365295,0.0001746701,0.00000135419,0.00009703799,0.000165664,0.00002937815,0.0003339074,2.005131e-7,0.0002959655,0.0003168351,0.986011,0.01233748],"study_design_scores_gemma":[0.0005041924,0.0006209975,0.0007892238,0.00005911489,0.00003395468,0.0002231081,0.0001904492,0.00002165566,0.00006800475,0.0001203425,0.9971833,0.0001856451],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.003949157,0.0005053845,0.00005991188,0.0004609592,0.0005056972,0.0005195599,0.986504,0.0001074012,0.007387884],"genre_scores_gemma":[0.002942056,0.001151727,0.00004330749,0.00006566869,0.000513113,1.34001e-7,0.9932463,0.0007093523,0.001328347],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02495886,"threshold_uncertainty_score":0.999074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04710374390200497,"score_gpt":0.3268899103009722,"score_spread":0.2797861663989673,"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."}}