{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009640281,0.001210706,0.0007568301,0.0003328733,0.0002847817,0.0006504373,0.0005347963,0.0006329317,0.002066059],"category_scores_gemma":[0.003443573,0.0002081918,0.0008105167,0.0002443665,0.0003953586,0.0009391213,0.001162325,0.001048841,0.001543579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001552653,"about_ca_system_score_gemma":0.0003520017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009693622,"about_ca_topic_score_gemma":0.00160238,"domain_scores_codex":[0.9994017,0.0001520611,0.00004688301,0.000195748,0.0001325467,0.0000709458],"domain_scores_gemma":[0.9990835,0.0004331534,0.0000534758,0.0001443947,0.0002439292,0.00004155753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001245481,0.0003786251,0.002218435,0.0005076501,0.000128315,0.00048569,0.0006259341,0.02205832,0.5161442,0.0007677938,0.003977644,0.451462],"study_design_scores_gemma":[0.00008156086,0.001348031,0.01851246,0.0001218858,0.0003058758,0.001055981,0.0005841334,0.4766074,0.482743,0.002873869,0.0156128,0.0001530322],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3776987,0.002703559,0.6040628,0.0006365975,0.0008161133,0.0003398378,0.001010993,0.006017799,0.006713514],"genre_scores_gemma":[0.7678483,0.0008586564,0.2217601,0.0005770035,0.0001675945,0.0004199721,0.002190125,0.0004306156,0.005747548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002066059,"threshold_uncertainty_score":0.006911635,"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."}}