{"id":"W2137997377","doi":"10.1109/icassp.2013.6639126","title":"Multiple windowed spectral features for emotion recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Institut National de la Recherche Scientifique; Computer Research Institute of Montréal","funders":"","keywords":"Multitaper; Mel-frequency cepstrum; Speech recognition; Computer science; Pattern recognition (psychology); Mixture model; Dynamic time warping; Feature (linguistics); Set (abstract data type); Artificial intelligence; Cepstrum; Feature extraction","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004533964,0.0005252608,0.0004937348,0.0009194726,0.0001461216,0.0005140547,0.0003348821,0.0004331438,0.003550123],"category_scores_gemma":[0.001154763,0.0001787279,0.000428129,0.0008536433,0.000119381,0.0008919333,0.0003411339,0.000363262,0.001378842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001790223,"about_ca_system_score_gemma":0.000165544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008645641,"about_ca_topic_score_gemma":0.001131977,"domain_scores_codex":[0.999686,0.00006769969,0.00002450279,0.00008595463,0.0001091975,0.00002668366],"domain_scores_gemma":[0.9995534,0.0001933291,0.00003961535,0.00006582167,0.0001322378,0.00001561351],"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":[0.0004516691,0.00009450025,0.0008688747,0.0001772429,0.00006461361,0.0001026985,0.00005767728,0.009884548,0.1697289,0.001072139,0.00231225,0.815185],"study_design_scores_gemma":[0.00008156167,0.0006643896,0.02313647,0.00008405447,0.0002341884,0.0006945566,0.0001638378,0.7449187,0.2014787,0.004315915,0.02410487,0.000122797],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1907354,0.004816265,0.7953279,0.0002164233,0.0002961075,0.0001526365,0.001314547,0.004006322,0.00313438],"genre_scores_gemma":[0.6098841,0.00166631,0.3817199,0.00006599634,0.0001463133,0.0001808223,0.001798155,0.0002996274,0.004238878],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003550123,"threshold_uncertainty_score":0.01187629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02811234192965691,"score_gpt":0.2315257983846509,"score_spread":0.203413456454994,"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."}}