{"id":"W4389752793","doi":"10.1016/j.eswa.2023.122946","title":"MSER: Multimodal speech emotion recognition using cross-attention with deep fusion","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":137,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Ministry of Science and ICT, South Korea; State Fund for Fundamental Research of Ukraine","keywords":"Computer science; Discriminative model; Robustness (evolution); Speech recognition; Artificial intelligence; Encoder; Feature (linguistics); Fusion mechanism; Pattern recognition (psychology); Fusion","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":[0.0009895015,0.001522415,0.001091687,0.0008449072,0.000323135,0.0007719896,0.001000862,0.001089815,0.01026256],"category_scores_gemma":[0.001120752,0.0003676234,0.0009585264,0.0006077277,0.0002080037,0.001099935,0.00200229,0.001287875,0.005414827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000374916,"about_ca_system_score_gemma":0.0004510169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0034619,"about_ca_topic_score_gemma":0.006195279,"domain_scores_codex":[0.999486,0.00007473661,0.0000263265,0.0001730772,0.000142159,0.000097709],"domain_scores_gemma":[0.9997194,0.0000863225,0.00001795289,0.00004842877,0.00009779307,0.00002998646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000923071,0.0004440573,0.001517215,0.0002095523,0.0002854437,0.0002306489,0.00008558307,0.009229257,0.09884325,0.001571376,0.03318695,0.8534737],"study_design_scores_gemma":[0.0001194508,0.0005961608,0.01061553,0.00006639655,0.00022656,0.0004796032,0.0001084023,0.8657713,0.09855048,0.005478774,0.01786043,0.0001268737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08601354,0.003077655,0.8454103,0.0006198844,0.001304182,0.0005226515,0.008139846,0.04523836,0.009673579],"genre_scores_gemma":[0.419582,0.001232921,0.5281466,0.001267382,0.0004612667,0.0008101912,0.01840863,0.001568087,0.02852301],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01026256,"threshold_uncertainty_score":0.03433162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05091831193250718,"score_gpt":0.3489223053887625,"score_spread":0.2980039934562553,"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."}}