{"id":"W2016053816","doi":"10.1007/s10772-012-9186-9","title":"MCRA noise estimation for KLT-VRE-based speech enhancement","year":2013,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Noise (video); Estimation; Speech enhancement; Artificial intelligence; Pattern recognition (psychology); Noise reduction","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":[0.0003385924,0.000153921,0.0002215376,0.0008407919,0.00007117983,0.0002359557,0.001862505,0.0001398506,0.0001165906],"category_scores_gemma":[0.0003288907,0.0001362852,0.0001218258,0.0003331422,0.000076652,0.0008470313,0.0001413919,0.0002471309,0.00009086724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001852664,"about_ca_system_score_gemma":0.0001999644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009399851,"about_ca_topic_score_gemma":0.000003485846,"domain_scores_codex":[0.9983395,0.00001361036,0.0005883451,0.0002322492,0.0005584691,0.0002677959],"domain_scores_gemma":[0.9975036,0.00009150636,0.0006195641,0.0002540952,0.00145893,0.00007226517],"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":[0.0000240296,0.0001320083,0.0005131642,0.00001137158,0.00006941082,0.00005756204,0.0000311925,0.0001682759,0.06267606,0.001928222,0.002663014,0.9317257],"study_design_scores_gemma":[0.001131041,0.0003147283,0.0002251339,0.0001203631,0.000009864285,0.0003994457,0.0000270508,0.01424452,0.9021384,0.07533997,0.005886765,0.0001626743],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09264034,0.0001390984,0.8716668,0.03384253,0.001144755,0.0002070724,0.000001950588,0.00009594494,0.000261524],"genre_scores_gemma":[0.4412776,0.00001397364,0.5578227,0.0005504243,0.0001851458,0.00002021676,0.000002498369,0.000008746184,0.0001187101],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.931563,"threshold_uncertainty_score":0.5557548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00989396939828999,"score_gpt":0.2753188794034044,"score_spread":0.2654249100051144,"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."}}