{"id":"W2068523583","doi":"10.1007/s11265-009-0374-z","title":"Feature Fusion Applied to Missing Data ASR with the Combination of Recognizers","year":2009,"lang":"en","type":"article","venue":"Journal of Signal Processing Systems","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Speech recognition; Computer science; Pattern recognition (psychology); Noise (video); Mel-frequency cepstrum; Artificial intelligence; Feature (linguistics); Cepstrum; Fusion; Process (computing); Hidden Markov model; Feature extraction","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":[0.001452101,0.0001521156,0.0003247737,0.0001896211,0.0002590289,0.0005743243,0.00150097,0.00006620626,8.458607e-7],"category_scores_gemma":[0.00003982347,0.00008725752,0.00003424536,0.0007865663,0.00003577349,0.001060642,0.00008641764,0.0002911548,0.00000116139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004881887,"about_ca_system_score_gemma":0.0003294818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001899047,"about_ca_topic_score_gemma":4.68601e-7,"domain_scores_codex":[0.9982615,0.00006529776,0.0004088823,0.0002422415,0.0008062613,0.0002157869],"domain_scores_gemma":[0.9978002,0.00007406795,0.001117116,0.0003374423,0.00055518,0.0001159428],"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":[0.0001686573,0.0001289907,0.00008701777,0.0002398537,0.00003321865,0.00003212285,0.001681758,0.002082335,0.1503476,0.0001123769,0.007012792,0.8380733],"study_design_scores_gemma":[0.01313217,0.009001801,0.008562248,0.03511011,0.0007090316,0.007834013,0.010938,0.2323083,0.6345618,0.006886851,0.03755642,0.003399303],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02680967,0.001990073,0.9568889,0.01283509,0.0001868839,0.0002358627,0.000001770333,0.00003834675,0.001013446],"genre_scores_gemma":[0.9647801,0.000004709094,0.03456873,0.0003648073,0.0002080417,7.625992e-7,0.000001608752,0.000008887549,0.00006236184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9379704,"threshold_uncertainty_score":0.5538223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02352298276305343,"score_gpt":0.2572750499648186,"score_spread":0.2337520672017652,"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."}}