{"id":"W141927798","doi":"10.21437/interspeech.2009-111","title":"Cepstral and long-term features for emotion recognition","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Mel-frequency cepstrum; Term (time); Speech recognition; Emotion recognition; Cepstrum; Recall; Artificial intelligence; Class (philosophy); Pattern recognition (psychology); Logistic regression; Machine learning; Feature extraction; Cognitive psychology; Psychology","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":[0.00009339899,0.00006569568,0.0000672745,0.00006301414,0.00007159679,0.0001393167,0.0001003,0.00004624508,0.00005329942],"category_scores_gemma":[0.00002982101,0.00005620228,0.00003952546,0.00007070115,0.00001028171,0.0003136206,0.00001040552,0.00003315576,0.00002272627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008398992,"about_ca_system_score_gemma":0.000007257846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001356411,"about_ca_topic_score_gemma":0.000005929318,"domain_scores_codex":[0.9995136,0.00001551463,0.00008367978,0.0001894938,0.00007432698,0.0001233457],"domain_scores_gemma":[0.999722,0.00004658831,0.00002549636,0.0001007966,0.00004997237,0.0000551458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000004828335,0.00002586147,0.0001443518,0.000003978581,0.000002639835,0.000001587466,0.00003956281,3.317274e-8,0.0006923684,0.00179649,0.0009046172,0.9963837],"study_design_scores_gemma":[0.001107479,0.0004916587,0.848985,0.00006151931,0.00002107138,0.0002079919,0.00003840714,0.002464846,0.08009604,0.06572946,0.0003490934,0.000447428],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2751258,0.00004971524,0.7108231,0.003920053,0.0002213844,0.0003153882,0.000005271424,0.0002929759,0.009246339],"genre_scores_gemma":[0.8473728,0.00003214566,0.1500879,0.001453577,0.00009908026,0.000009519707,0.00001555935,0.000003473215,0.0009259931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9959363,"threshold_uncertainty_score":0.2291862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03399994574915362,"score_gpt":0.2703713796623454,"score_spread":0.2363714339131917,"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."}}