{"id":"W2376759433","doi":"","title":"A speech enhancement algorithm based on linear prediction residual","year":2011,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Linear prediction; Residual; Computer science; Speech enhancement; Intelligibility (philosophy); Algorithm; Noise reduction; Formant; Wiener filter; Speech recognition; Linear predictive coding; Mean squared error; Computation; Filter (signal processing); Minimum mean square error; Noise (video); Speech processing; Mathematics; Artificial intelligence; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001560258,0.0001621026,0.0001174173,0.0001505896,0.0002298052,0.00009907396,0.0007444999,0.00006391996,0.0000347171],"category_scores_gemma":[5.579703e-7,0.0001587232,0.00005400075,0.0003922523,0.00003410133,0.0002281316,0.0001340883,0.0001448049,0.0003568259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005455112,"about_ca_system_score_gemma":0.00008042098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001121167,"about_ca_topic_score_gemma":0.000001249204,"domain_scores_codex":[0.9986861,0.00002564262,0.0002507303,0.0005386922,0.0002215649,0.0002772241],"domain_scores_gemma":[0.9990998,0.00002748994,0.00009310037,0.0005618426,0.0001154726,0.0001022985],"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":[0.000003573998,0.0003477052,0.00009737757,0.00001059046,0.00001015907,0.000004153463,0.0001925951,0.00004243388,0.005386786,0.0004638937,0.001701363,0.9917394],"study_design_scores_gemma":[0.0005689212,0.0002086769,0.001347831,0.00004321225,0.0000117077,0.00001531742,0.000007472761,0.08398949,0.7300608,0.001964618,0.181464,0.0003179662],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008471091,0.00002774412,0.9954603,0.0003826644,0.00004555502,0.0004462705,0.000009627632,0.0003396748,0.00244103],"genre_scores_gemma":[0.00641979,0.000003898713,0.9915605,0.001280275,0.0002839073,0.0002862597,0.00001986079,0.00001295254,0.0001325314],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9914214,"threshold_uncertainty_score":0.6472545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02008411048548263,"score_gpt":0.2382517675886448,"score_spread":0.2181676571031622,"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."}}