{"id":"W2883496341","doi":"10.1109/taffc.2018.2858255","title":"Feature Pooling of Modulation Spectrum Features for Improved Speech Emotion Recognition in the Wild","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Affective Computing","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Reverberation; Pooling; Computer science; Speech recognition; Benchmark (surveying); Affective computing; Noise (video); Feature (linguistics); Valence (chemistry); Background noise; Artificial intelligence; Feature extraction; Engineering; Telecommunications","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":[0.00063681,0.0001810844,0.0001988853,0.0003302602,0.0002807596,0.00002896177,0.0001067155,0.000203844,0.00005222023],"category_scores_gemma":[0.00002798641,0.0001562216,0.0001652933,0.0004624648,0.00007896773,0.0001088659,0.000001046186,0.0003934518,0.0000251319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008520892,"about_ca_system_score_gemma":0.00001588055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008733662,"about_ca_topic_score_gemma":0.0003310394,"domain_scores_codex":[0.9986768,0.0003322581,0.0002274846,0.000369179,0.0001273014,0.0002669248],"domain_scores_gemma":[0.9989511,0.0004493799,0.0001904242,0.0001964734,0.0001822135,0.00003039504],"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":[0.0006710119,0.0007039527,0.00006787459,0.00005523861,0.0001173682,0.000001673355,0.006367992,0.0009595028,0.01173142,0.0001875888,0.0005398195,0.9785966],"study_design_scores_gemma":[0.01938403,0.01059461,0.285642,0.002017106,0.0007064206,0.0005410935,0.01533927,0.2383239,0.4037006,0.02097705,0.0006104668,0.002163404],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3928598,0.00001139622,0.6026707,0.0006204379,0.001468917,0.0009596157,0.00003473129,0.0000649633,0.001309529],"genre_scores_gemma":[0.9969174,0.000003799672,0.002121571,0.0002815563,0.0004507274,0.00004015979,0.0000350906,0.00002684781,0.0001228303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9764332,"threshold_uncertainty_score":0.6370532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02867653713525803,"score_gpt":0.3116998049138324,"score_spread":0.2830232677785743,"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."}}