{"id":"W3088789516","doi":"10.3390/s20195559","title":"Fusing Visual Attention CNN and Bag of Visual Words for Cross-Corpus Speech Emotion Recognition","year":2020,"lang":"en","type":"article","venue":"Sensors","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Iran Telecommunication Research Center","keywords":"Computer science; Convolutional neural network; Utterance; Spectrogram; Speech recognition; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Bag-of-words model in computer vision; Channel (broadcasting); Generalization; Histogram; Natural language processing; Visual Word; Image (mathematics); Image retrieval; Mathematics","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":[0.0002233929,0.0001400449,0.0001958555,0.0001132682,0.0001202954,0.00004826637,0.00003380567,0.0001784852,0.0003569781],"category_scores_gemma":[0.000122448,0.0001515597,0.0001067242,0.0001838562,0.0001048418,0.000115301,0.00001771057,0.0001201047,0.000138946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001916623,"about_ca_system_score_gemma":0.00001301345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002885185,"about_ca_topic_score_gemma":0.000008190415,"domain_scores_codex":[0.9988382,0.0001084107,0.0003499264,0.0003533554,0.0001393299,0.0002107239],"domain_scores_gemma":[0.9993863,0.000073744,0.0001965585,0.00006927726,0.0001887795,0.00008537148],"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":[0.001512022,0.0006000917,0.009852774,0.0004004828,0.0001693181,0.00001799741,0.004652021,0.00002523352,0.1035461,0.0003026697,0.0008080508,0.8781132],"study_design_scores_gemma":[0.03391164,0.01187358,0.6580906,0.001058529,0.001158067,0.0005324389,0.01905854,0.04399738,0.2053876,0.007486443,0.01427086,0.003174335],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993596,0.00003589903,0.002704117,0.0003470563,0.0009229642,0.0004503157,0.0000370418,0.00009551028,0.001811062],"genre_scores_gemma":[0.9972208,0.0000176613,0.001008544,0.0003340943,0.0004385393,0.00001229534,0.0002642346,0.00003133881,0.0006724885],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8749389,"threshold_uncertainty_score":0.6180424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05612792339920404,"score_gpt":0.3633029550649556,"score_spread":0.3071750316657516,"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."}}