{"id":"W4361224703","doi":"10.3389/fcomp.2023.1039261","title":"Task-specific speech enhancement and data augmentation for improved multimodal emotion recognition under noisy conditions","year":2023,"lang":"en","type":"article","venue":"Frontiers in Computer Science","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Speech recognition; Robustness (evolution); Speech enhancement; Task (project management); Modalities; Noise (video); Artificial intelligence; Speech processing; Voice activity detection; Noise reduction","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":[],"consensus_categories":[],"category_scores_codex":[0.0008344132,0.0001143539,0.0001247283,0.0004760838,0.0002488212,0.0001078366,0.0002881709,0.00006697583,0.00005381583],"category_scores_gemma":[0.00001759922,0.0001239896,0.00002237659,0.0006966796,0.0002282957,0.0005653981,0.0001332432,0.00009328993,0.00007468275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009923306,"about_ca_system_score_gemma":0.00003946704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001745911,"about_ca_topic_score_gemma":0.00001184298,"domain_scores_codex":[0.9984766,0.00005986402,0.0002591778,0.0007229506,0.0001639651,0.0003173885],"domain_scores_gemma":[0.9993121,0.00004835846,0.00009880655,0.0003545266,0.0001093693,0.00007685454],"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":[0.00005546938,0.0001925822,0.0003155599,0.00001832376,0.00002031718,0.000002837779,0.001113214,0.00006019393,0.008074442,0.0002479817,0.04840658,0.9414925],"study_design_scores_gemma":[0.005727059,0.0005089031,0.07600224,0.0001285569,0.00002973712,0.00002825588,0.00188224,0.8855981,0.003463972,0.02130633,0.004704637,0.0006199569],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1422279,0.00004076512,0.850148,0.0006297287,0.005878057,0.0006946393,0.0001577098,0.00008842563,0.0001348646],"genre_scores_gemma":[0.6072324,0.0002633154,0.3865786,0.0008247034,0.0004846282,0.0002024032,0.004040827,0.00002736699,0.0003457301],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9408726,"threshold_uncertainty_score":0.5056147,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0780036761846626,"score_gpt":0.3581432731810522,"score_spread":0.2801395969963896,"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."}}