{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005201864,0.0009282313,0.0004818348,0.0004371277,0.0001837991,0.0008100079,0.0007334439,0.0005288258,0.003688191],"category_scores_gemma":[0.001582545,0.0002460066,0.0005987932,0.0002068853,0.0002609668,0.00114817,0.001152438,0.001216624,0.002196706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002203598,"about_ca_system_score_gemma":0.0002577723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007038108,"about_ca_topic_score_gemma":0.001465094,"domain_scores_codex":[0.9996539,0.00006605695,0.0000146927,0.0001518176,0.00007053419,0.00004301664],"domain_scores_gemma":[0.9997312,0.00009620061,0.0000227597,0.00004939116,0.00007976132,0.00002071606],"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":[0.000515501,0.0002242426,0.001738637,0.0001620137,0.000105085,0.0001669791,0.0002496118,0.02375707,0.1390142,0.004044857,0.00818034,0.8218415],"study_design_scores_gemma":[0.00003205974,0.0002700811,0.004591286,0.0000389748,0.00009412246,0.0002021031,0.0001769174,0.9078401,0.06703868,0.01122134,0.008443024,0.00005130641],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05455456,0.0008548405,0.9310521,0.000366138,0.0002202992,0.00008694644,0.0005650383,0.005661454,0.006638643],"genre_scores_gemma":[0.6929109,0.0005936455,0.291494,0.0005687614,0.0002032992,0.0001996995,0.002217526,0.000372614,0.01143964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003688191,"threshold_uncertainty_score":0.01233822,"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."}}