{"id":"W2528939255","doi":"10.1109/taffc.2017.2763132","title":"Feature Learning from Spectrograms for Assessment of Personality Traits","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Affective Computing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Spectrogram; Computer science; Feature extraction; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Speech recognition; Set (abstract data type); Linear discriminant analysis; Parameterized complexity; Process (computing); Algorithm","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":[0.0003635002,0.0001826159,0.0002795017,0.00007579799,0.001277936,0.0003273762,0.0006310611,0.00008253237,0.000005054606],"category_scores_gemma":[0.00003204292,0.0001785326,0.000226127,0.0001138779,0.00007952782,0.000367172,0.000007660988,0.0004305427,0.000001771558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009625001,"about_ca_system_score_gemma":0.00008108422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006012125,"about_ca_topic_score_gemma":0.00004072725,"domain_scores_codex":[0.9987387,0.00009047936,0.000141797,0.0004865289,0.0002457375,0.0002967627],"domain_scores_gemma":[0.9986885,0.0004502327,0.0003065219,0.0003349935,0.0001433646,0.00007644446],"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":[0.00002860189,0.0002607472,0.001677388,0.00006188684,0.0001669989,0.000004962428,0.001073456,0.01211271,0.0347638,0.0002502121,0.00003431517,0.9495649],"study_design_scores_gemma":[0.001683463,0.0006256594,0.1136378,0.0003412389,0.00006044363,0.000009168797,0.0001719986,0.3811418,0.5006208,0.00109609,0.0001733003,0.0004382635],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.197146,0.00002435093,0.8011419,0.0004148831,0.0003985619,0.0002304162,0.000007688831,0.0001211702,0.0005149586],"genre_scores_gemma":[0.851099,0.000002133087,0.1486866,0.00003747406,0.0001023955,0.00001024957,0.000001124059,0.00001201947,0.00004901057],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9491267,"threshold_uncertainty_score":0.982898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03554585514234741,"score_gpt":0.3259179887493793,"score_spread":0.2903721336070319,"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."}}