{"id":"W2112089769","doi":"","title":"ALGONQUIN - Learning Dynamic Noise Models From Noisy Speech for Robust Speech Recognition","year":2001,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Speech recognition; Computer science; Noise (video); Utterance; Noise measurement; Speech enhancement; Background noise; Cepstrum; Speech processing; 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":[0.000316335,0.0002308167,0.0002359855,0.0001516503,0.0002843594,0.0004197623,0.0006484338,0.0001288465,0.0001386542],"category_scores_gemma":[0.00007686239,0.0002213418,0.0001130294,0.0004351821,0.00003065457,0.001616185,0.0001569535,0.0002317048,0.0002172853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008431323,"about_ca_system_score_gemma":0.00007445648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000160011,"about_ca_topic_score_gemma":0.0001218033,"domain_scores_codex":[0.9981291,0.0000420699,0.0003166242,0.0006863322,0.0003040709,0.000521827],"domain_scores_gemma":[0.9990072,0.000151126,0.0001387884,0.0003692528,0.0001893282,0.0001442502],"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":[0.00002403287,0.00006480468,0.0001342691,0.00001198285,0.00001736922,0.00003742729,0.0001795933,0.003710125,0.01052607,0.00004039049,0.0005495531,0.9847044],"study_design_scores_gemma":[0.000773098,0.0001001016,0.0001066283,0.00006885501,0.00001632479,0.0000630262,0.000109711,0.8852023,0.07480445,0.03732061,0.001014709,0.0004201425],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1460661,0.0001290614,0.8459066,0.0007586527,0.0002542966,0.0002327031,0.000006407548,0.0004866944,0.006159415],"genre_scores_gemma":[0.1335848,0.00008094464,0.8626742,0.0005553989,0.0001849197,0.00002773727,0.00008533298,0.00003054419,0.002776061],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9842842,"threshold_uncertainty_score":0.9026055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04078171902559141,"score_gpt":0.2557413811212836,"score_spread":0.2149596620956922,"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."}}