{"id":"W2944426940","doi":"10.1109/taslp.2019.2912123","title":"Non-Intrusive Speech Quality Prediction Using Modulation Energies and LSTM-Network","year":2019,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft","keywords":"Computer science; Speech recognition; Benchmark (surveying); Measure (data warehouse); Reverberation; Quality (philosophy); Speech processing; Noise (video); Range (aeronautics); Artificial neural network; SIGNAL (programming language); PESQ; Speech enhancement; Sound quality; Energy (signal processing); Artificial intelligence; Data mining; Noise reduction; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004969473,0.0003533063,0.000388843,0.0002511259,0.0006498719,0.000602306,0.000361914,0.0001973426,0.00003331047],"category_scores_gemma":[0.00002904554,0.0003397524,0.00008024353,0.0006970126,0.00009384743,0.001520707,0.00003199327,0.0003940641,0.00001412921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009916982,"about_ca_system_score_gemma":0.0001369394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001063178,"about_ca_topic_score_gemma":0.00004590217,"domain_scores_codex":[0.9976717,0.00007536435,0.0004521504,0.0008263217,0.0004353867,0.000539082],"domain_scores_gemma":[0.9987506,0.00009705446,0.0002631985,0.0005591967,0.0001466627,0.0001832504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006609257,0.00008185864,0.001869787,0.0003046798,0.00004659559,0.00002807406,0.002586262,0.01366965,0.09222335,0.00001314459,0.00001782319,0.8890927],"study_design_scores_gemma":[0.002476134,0.0003466969,0.009719819,0.001168935,0.0001192868,0.0005680285,0.001822441,0.3510799,0.6288507,0.002326151,0.0001947863,0.001327134],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5369194,0.0007387095,0.4612267,0.0001629741,0.0003228737,0.0002071935,0.000007298151,0.0002075178,0.000207279],"genre_scores_gemma":[0.8499544,0.00008745301,0.1490427,0.000340136,0.0002270276,0.00001077416,0.000005253133,0.00002942526,0.0003028391],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8877655,"threshold_uncertainty_score":0.9999055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0147511386327966,"score_gpt":0.272053899695278,"score_spread":0.2573027610624814,"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."}}