{"id":"W177255557","doi":"10.21437/interspeech.2004-99","title":"Noise adaptation for robust AURORA 2 noisy digit recognition using statistical data mapping","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec","funders":"","keywords":"Computer science; Speech recognition; Noise (video); Adaptation (eye); Digit recognition; Feature (linguistics); Pattern recognition (psychology); Artificial intelligence; Noisy data; Noise measurement; Feature extraction; Noise reduction; Artificial neural network","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":[0.0001875783,0.0001028467,0.0001046287,0.00007888617,0.0001848067,0.0003977441,0.0005017035,0.00004071342,0.00001191248],"category_scores_gemma":[0.0001910359,0.00009882748,0.00001894919,0.000244762,0.00002430854,0.001783894,0.0001812993,0.00006225598,0.00002929746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006258561,"about_ca_system_score_gemma":0.0001787742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005039118,"about_ca_topic_score_gemma":0.00002784818,"domain_scores_codex":[0.9989025,0.00001229559,0.0002129753,0.0004368151,0.0001795984,0.0002558374],"domain_scores_gemma":[0.9992555,0.00008653697,0.00008030595,0.0003822129,0.0001143356,0.00008111714],"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":[0.0000111034,0.00007377432,0.00003011238,0.00005259148,0.00001245974,0.00001233065,0.0002886065,0.008008422,0.004530573,0.001308032,0.0003048304,0.9853672],"study_design_scores_gemma":[0.0009709016,0.00006282939,0.0001598259,0.0001295476,0.00001627007,0.00003658703,0.0001783228,0.9447842,0.02417402,0.02831309,0.0008388459,0.0003355634],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009149605,0.00001948504,0.9894049,0.0004516732,0.000167335,0.0001737034,0.00003741646,0.0001619696,0.0004338926],"genre_scores_gemma":[0.08083053,0.000002598772,0.9185232,0.0003254323,0.0001046078,0.000005427166,0.0001777325,0.000009282576,0.00002119338],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9850316,"threshold_uncertainty_score":0.4030068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.244781941041828,"score_gpt":0.3129141343636097,"score_spread":0.06813219332178161,"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."}}