{"id":"W2289179757","doi":"10.1049/iet-spr.2014.0148","title":"Modified coherence‐based dictionary learning method for speech enhancement","year":2015,"lang":"en","type":"article","venue":"IET Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Langley Research Center","keywords":"Computer science; Sparse approximation; Coherence (philosophical gambling strategy); K-SVD; Speech recognition; Noise (video); Speech enhancement; Artificial intelligence; Context (archaeology); Pattern recognition (psychology); Energy (signal processing); Noise reduction; Algorithm; Mathematics; Statistics","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":[0.001123328,0.0002290463,0.000250222,0.0001394107,0.0004479176,0.0004798004,0.0006015237,0.00009572688,0.00001488621],"category_scores_gemma":[0.0001023863,0.0002142822,0.00008068496,0.0005062636,0.00004297946,0.0009089024,0.0001074413,0.0002504234,0.00001990262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00011781,"about_ca_system_score_gemma":0.0006411056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000113484,"about_ca_topic_score_gemma":0.000001069123,"domain_scores_codex":[0.9979531,0.00009256004,0.0003417883,0.0005937152,0.0005265794,0.0004923143],"domain_scores_gemma":[0.998751,0.000153337,0.000250234,0.0001912528,0.0004296724,0.0002245267],"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":[0.0000737881,0.0001131279,0.0001303745,0.0001372067,0.00001515228,0.00001490899,0.0006341108,0.01839823,0.03893933,0.0001225278,0.0009449779,0.9404762],"study_design_scores_gemma":[0.0008771948,0.0002534084,0.00001117695,0.000139118,0.0000136371,0.00001798719,0.0001043972,0.6773112,0.3100613,0.007634817,0.003278829,0.0002969248],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002035801,0.0006147144,0.9925401,0.0006858992,0.0001727336,0.0002553494,0.000001099984,0.0003434963,0.003350873],"genre_scores_gemma":[0.4424323,8.272493e-7,0.5564316,0.0004664468,0.000165814,0.00006376024,0.000008844396,0.00001626742,0.0004141511],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9401793,"threshold_uncertainty_score":0.8738173,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0637031942681851,"score_gpt":0.3303900956719341,"score_spread":0.266686901403749,"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."}}