{"id":"W2158710177","doi":"10.1109/icassp.2004.1326153","title":"Nonlinear noise compensation in feature domain for speech recognition with numerical methods","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Nonlinear system; Nonlinear distortion; Taylor series; Speech recognition; Noise (video); Distortion (music); White noise; Speech enhancement; Minimum mean square error; Additive white Gaussian noise; Feature (linguistics); Frequency domain; Algorithm; Mean squared error; Domain (mathematical analysis); Artificial intelligence; Pattern recognition (psychology); Mathematics; Noise reduction; Telecommunications; Computer vision; 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":[0.0003514139,0.00009982578,0.0001314711,0.000090565,0.00006743007,0.0001096609,0.0002010106,0.00006067548,0.000005714088],"category_scores_gemma":[0.00003780194,0.0000759625,0.00002949561,0.0004710022,0.000017122,0.0004609983,0.00003038497,0.000111579,0.00001310944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006347922,"about_ca_system_score_gemma":0.00008618081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001975794,"about_ca_topic_score_gemma":0.00003739152,"domain_scores_codex":[0.9992172,0.0000386455,0.0001228385,0.0002865401,0.0001316841,0.0002031553],"domain_scores_gemma":[0.9995813,0.0000713256,0.00005677501,0.0001545736,0.00008213281,0.00005393071],"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":[0.00007993889,0.0001931939,0.0003363738,0.00003256222,0.000009112334,0.00002464169,0.000452942,0.0002398345,0.01501125,0.001196299,0.0001204403,0.9823034],"study_design_scores_gemma":[0.002697118,0.0003510579,0.001166207,0.0001141411,0.000006026797,0.0001054634,0.0001061224,0.009043222,0.9299453,0.05465946,0.001469815,0.0003360792],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0331995,0.00002712565,0.962036,0.003447916,0.00006472033,0.000224343,0.000001278044,0.0001004136,0.0008987569],"genre_scores_gemma":[0.01547871,0.000001571064,0.9836695,0.0006956338,0.00006358579,0.000018782,0.00001309654,0.000007556064,0.00005153423],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9819673,"threshold_uncertainty_score":0.3097661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02498209158015554,"score_gpt":0.3126596209044535,"score_spread":0.287677529324298,"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."}}