{"id":"W4392904321","doi":"10.1109/icassp48485.2024.10448505","title":"Speech Emotion Recognition with Distilled Prosodic and Linguistic Affect Representations","year":2024,"lang":"en","type":"article","venue":"","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Vector Institute; Mitacs","keywords":"Computer science; Speech recognition; Feature extraction; Inference; Margin (machine learning); Benchmark (surveying); Embedding; Artificial intelligence; Computation; Natural language processing; Machine learning; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001543626,0.0001049638,0.00009246337,0.0001507145,0.00008350352,0.00009139187,0.00002522073,0.00006966321,0.002234118],"category_scores_gemma":[0.00007384348,0.0000803372,0.00003179351,0.0002296178,0.00006126169,0.00008024491,0.00000960791,0.0001310615,0.0007278859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000177761,"about_ca_system_score_gemma":0.00001733292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000826408,"about_ca_topic_score_gemma":0.00007884347,"domain_scores_codex":[0.9991804,0.00008619741,0.0001440474,0.0003463436,0.000103899,0.0001391384],"domain_scores_gemma":[0.9996011,0.0001174071,0.00002786001,0.0001219109,0.00006589384,0.00006585396],"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":[0.0003208517,0.0005485587,0.00443423,0.0005001536,0.0003790894,0.0004938215,0.008848246,0.000001990684,0.001853828,0.02999115,0.01345416,0.9391739],"study_design_scores_gemma":[0.01812764,0.008460609,0.6680728,0.005679615,0.003417364,0.01058024,0.01983617,0.01134099,0.01361093,0.1868222,0.04897241,0.005079028],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5874917,0.0002638928,0.01731731,0.0006249514,0.001379706,0.0007711573,0.00003025863,0.0006616287,0.3914594],"genre_scores_gemma":[0.9874735,0.00002914557,0.001200372,0.00009768293,0.0002403128,0.00007665833,0.0001792189,0.00002149612,0.01068156],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9340949,"threshold_uncertainty_score":0.998678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03803445897420302,"score_gpt":0.3428931580891779,"score_spread":0.3048586991149749,"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."}}