{"id":"W4308630605","doi":"10.7717/peerj-cs.1091","title":"Feature selection enhancement and feature space visualization for speech-based emotion recognition","year":2022,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Feature (linguistics); Set (abstract data type); Emotion recognition; Feature selection; Pattern recognition (psychology); Artificial intelligence; Feature vector; Speech processing; Visualization","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007853823,0.0001312964,0.0001124263,0.0003130307,0.0008141019,0.0001147121,0.0001383437,0.00006221598,0.000242103],"category_scores_gemma":[0.00002606488,0.0001400659,0.0000458981,0.0007999215,0.00009339766,0.0002228852,0.00006539241,0.0001697426,0.00001961557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001540806,"about_ca_system_score_gemma":0.00007239468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001052805,"about_ca_topic_score_gemma":0.000007872842,"domain_scores_codex":[0.99851,0.0001244148,0.0001136555,0.0005767525,0.0003974289,0.0002777565],"domain_scores_gemma":[0.9993051,0.00004634656,0.0001360161,0.0001366619,0.0002928427,0.00008306396],"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":[0.0003502343,0.0008582899,0.0008508429,0.0001121895,0.00003812919,0.000006271068,0.003153433,0.0008138021,0.03832557,0.004736854,0.104038,0.8467163],"study_design_scores_gemma":[0.00813087,0.006123499,0.03952892,0.0001562657,0.0001683176,0.0005265267,0.001048682,0.7186159,0.07649776,0.005271207,0.1423294,0.001602637],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.178175,0.00005230684,0.8128912,0.004559007,0.002786732,0.0007959621,0.00002957992,0.0001550441,0.000555116],"genre_scores_gemma":[0.9312012,0.000006716055,0.06188444,0.002265829,0.0005176676,0.000280111,0.0004630758,0.0000264491,0.003354507],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8451138,"threshold_uncertainty_score":0.6261496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02845440566603689,"score_gpt":0.3187630918992309,"score_spread":0.290308686233194,"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."}}