{"id":"W1991766343","doi":"10.1109/acssc.2014.7094689","title":"Noise power spectral density matrix estimation based on modified IMCRA","year":2014,"lang":"en","type":"article","venue":"2014 48th Asilomar Conference on Signals, Systems and Computers","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reverberation; Spectral density; Computer science; Noise (video); Noise power; Speech enhancement; Robustness (evolution); Value noise; Gradient noise; Diagonal; Noise measurement; Microphone array; Colors of noise; Diagonal matrix; Detector; Algorithm; Spectral density estimation; Microphone; Speech recognition; Acoustics; Mathematics; Background noise; Noise floor; Power (physics); Artificial intelligence; Noise reduction; Physics; Telecommunications","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":[0.0006554009,0.000388323,0.000483016,0.0002557776,0.0002958138,0.001005099,0.0006577413,0.0001360763,0.00001201158],"category_scores_gemma":[0.00003552085,0.0003372166,0.00009935701,0.0002101895,0.00007348669,0.0003823529,0.0001014312,0.0002362227,0.000153047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005917705,"about_ca_system_score_gemma":0.0001278358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006823135,"about_ca_topic_score_gemma":0.00000248903,"domain_scores_codex":[0.9974129,0.0002553641,0.0004301423,0.0008119793,0.0005871581,0.0005024888],"domain_scores_gemma":[0.9983124,0.0002167667,0.0003095019,0.0006858674,0.0001701844,0.0003053085],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006313481,0.001081657,0.003841542,0.0009050476,0.0002252463,0.000225104,0.001499541,0.2460884,0.02356018,0.4039115,0.02343296,0.2945975],"study_design_scores_gemma":[0.0008388195,0.0005703756,0.002975157,0.0003873156,0.00001001198,0.00002494528,0.00001996747,0.9893708,0.003511393,0.001616539,0.0002270565,0.0004475764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07680895,0.00007186598,0.9173176,0.0008928541,0.0008410407,0.000329167,0.000004087055,0.0002729517,0.003461511],"genre_scores_gemma":[0.9796108,0.000004850618,0.01939554,0.0007298205,0.0001251077,0.00001598688,0.000007222307,0.00001884388,0.00009182624],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9028019,"threshold_uncertainty_score":0.999908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01617940101138994,"score_gpt":0.2420667808475495,"score_spread":0.2258873798361596,"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."}}