{"id":"W2259805550","doi":"10.1049/iet-spr.2013.0392","title":"Optimisation of multiple feature stream weights for distributed speech processing in mobile environments","year":2015,"lang":"en","type":"article","venue":"IET Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Discriminative model; Computer science; Speech recognition; Hidden Markov model; Word error rate; Mel-frequency cepstrum; Speech processing; Pattern recognition (psychology); Noise (video); Feature extraction; Artificial intelligence","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":[0.0004494175,0.0002517189,0.0003235338,0.0001740801,0.0001621648,0.0002399643,0.000580223,0.0001567069,0.000002801421],"category_scores_gemma":[0.00009474912,0.0002317125,0.00006564282,0.0006121338,0.00007610537,0.001496299,0.0001167279,0.0001961652,0.000003224056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001631607,"about_ca_system_score_gemma":0.0003045056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000792209,"about_ca_topic_score_gemma":0.000006770213,"domain_scores_codex":[0.9980593,0.0000408961,0.0004204339,0.0005485073,0.0004736715,0.0004571986],"domain_scores_gemma":[0.9990023,0.00007177074,0.000388092,0.0002187373,0.0001573183,0.0001617924],"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":[0.000115736,0.0004177537,0.005590632,0.0003498262,0.000009312313,0.00001683129,0.00261037,0.008545315,0.04073338,0.00001310338,0.0002367478,0.941361],"study_design_scores_gemma":[0.002931077,0.0003228011,0.0010098,0.00078409,0.00002283828,0.00002978756,0.0006819027,0.333689,0.6538183,0.004154497,0.001989436,0.0005664714],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2053636,0.002064088,0.7914725,0.0001846182,0.00007427476,0.0005537312,0.00002014859,0.0001093022,0.0001577213],"genre_scores_gemma":[0.8271569,0.00000474299,0.1724938,0.00004673323,0.00008350323,0.0000698431,0.0000549352,0.00001999134,0.00006951988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9407945,"threshold_uncertainty_score":0.9448961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02169400304218556,"score_gpt":0.2583754798393787,"score_spread":0.2366814767971931,"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."}}