{"id":"W4387490008","doi":"10.1109/indiscon58499.2023.10270809","title":"Beyond Words: Extracting Emotions from Speech with AI Techniques","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Convolutional neural network; Mel-frequency cepstrum; Random forest; Categorization; Spectrogram; Speech recognition; Emotion classification; Artificial intelligence; Affective computing; Human voice; Python (programming language); Set (abstract data type); Emotion recognition; Artificial neural network; Feature extraction","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":[0.000149099,0.0001031679,0.00009695971,0.0001311205,0.0001943729,0.000357421,0.0004523644,0.00004329201,0.00009425292],"category_scores_gemma":[0.00003577213,0.00007960889,0.00002671844,0.0009425693,0.00002470999,0.0008327004,0.0001500433,0.0001514916,0.0003614685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000178949,"about_ca_system_score_gemma":0.00007582093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001191535,"about_ca_topic_score_gemma":0.00004977798,"domain_scores_codex":[0.999041,0.00001428444,0.0001235408,0.0003276065,0.0002348956,0.0002586728],"domain_scores_gemma":[0.9994016,0.00008481744,0.00004969211,0.0003340046,0.00005771868,0.00007217749],"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":[0.000003613836,0.00004250542,0.00198011,0.000007956473,0.00001938153,0.000192202,0.0008868755,0.000009818846,0.02551361,0.002656183,0.006621602,0.9620661],"study_design_scores_gemma":[0.0001449909,0.00007271792,0.001904679,0.00009845123,0.000006162394,0.00005979961,0.0004594533,0.001885178,0.9390409,0.0518947,0.004135064,0.0002979138],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1550009,0.00003248239,0.7490017,0.006948054,0.0001557994,0.0001311022,0.000001831878,0.003364175,0.08536394],"genre_scores_gemma":[0.4189223,0.00001002541,0.5760446,0.001534567,0.0001466459,0.00001151803,0.000005444017,0.00001341177,0.00331152],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9617682,"threshold_uncertainty_score":0.4646066,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01533547229936469,"score_gpt":0.2700569483987894,"score_spread":0.2547214760994247,"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."}}