{"id":"W2922332774","doi":"10.1109/icassp.2019.8683175","title":"Non-intrusive Speech Quality Assessment Using Neural Networks","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"PESQ; Mean opinion score; Computer science; Mean squared error; Artificial neural network; Speech recognition; Quality (philosophy); Correlation; Quality of experience; Artificial intelligence; Machine learning; Speech enhancement; Quality of service; Statistics; Noise reduction; Telecommunications; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003696062,0.0001384295,0.000195661,0.00005088733,0.0001089785,0.0003411258,0.0006100122,0.00005935804,0.0001213561],"category_scores_gemma":[0.000008216534,0.0001158885,0.00006804502,0.0003304984,0.00001949194,0.0006982721,0.0003251023,0.0001859582,0.00005054088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007120345,"about_ca_system_score_gemma":0.00009009268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008633314,"about_ca_topic_score_gemma":0.000007728978,"domain_scores_codex":[0.9986453,0.00004158362,0.0002375848,0.0004056141,0.0002958036,0.000374081],"domain_scores_gemma":[0.9991388,0.00005736531,0.0001183996,0.0004996377,0.00008926043,0.00009657201],"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":[0.00002634506,0.0002888339,0.2652771,0.0001316109,0.00009937392,0.0001248922,0.0005919145,0.06638083,0.06855799,0.01291525,0.00147438,0.5841315],"study_design_scores_gemma":[0.0003016856,0.00003766037,0.01571082,0.00001602017,0.000002943035,0.00002353067,0.00004546048,0.9689168,0.01395253,0.0006644733,0.000100128,0.0002279938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4685529,0.00001912533,0.5219061,0.0002655397,0.0005441972,0.0001048049,1.512264e-7,0.00009494222,0.008512201],"genre_scores_gemma":[0.8087536,0.000001317684,0.1896703,0.001076913,0.000117136,0.000001283971,8.793859e-7,0.000006594667,0.0003720406],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9025359,"threshold_uncertainty_score":0.4725795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03097023443026254,"score_gpt":0.3260866942796873,"score_spread":0.2951164598494248,"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."}}