{"id":"W2127008628","doi":"10.1109/icassp.2007.367251","title":"Combination of Recognizers and Fusion of Features Approach to Missing Data ASR Under Non-Stationary Noise Conditions","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Missing data; Noise (video); Speech recognition; Process (computing); Sensor fusion; Artificial intelligence; Fusion; Pattern recognition (psychology); Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001760274,0.0009070903,0.001285127,0.0007695807,0.0002977251,0.0009347902,0.001125863,0.001257023,0.0008683317],"category_scores_gemma":[0.004315483,0.0005506841,0.0008912974,0.0004944807,0.0006192036,0.00163108,0.001289541,0.001441901,0.0009877369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002464344,"about_ca_system_score_gemma":0.0005137966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000754195,"about_ca_topic_score_gemma":0.001114253,"domain_scores_codex":[0.9979589,0.0004482426,0.0001392719,0.0003778137,0.0009132958,0.0001624675],"domain_scores_gemma":[0.9979087,0.0006665682,0.0002207413,0.0006031874,0.0005373836,0.00006347425],"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":[0.000723184,0.0001951298,0.002487685,0.0002534916,0.0002628615,0.0004683762,0.0002786499,0.14234,0.1912111,0.007556851,0.001382613,0.6528401],"study_design_scores_gemma":[0.00001860201,0.0003561935,0.001404797,0.00001956337,0.0001123992,0.0009036465,0.00005445532,0.8497893,0.1415305,0.003628783,0.002120518,0.00006125332],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02569115,0.0002051589,0.9724684,0.00007816834,0.00004466957,0.00002118356,0.00002482871,0.0008322032,0.0006342363],"genre_scores_gemma":[0.5540735,0.0002819285,0.4425506,0.0001159199,0.00006699354,0.00004569102,0.0001671106,0.00008966752,0.002608623],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001760274,"threshold_uncertainty_score":0.009309351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03519762015747554,"score_gpt":0.3023354590177078,"score_spread":0.2671378388602323,"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."}}