{"id":"W2047310979","doi":"10.1049/el:20020242","title":"Unequal error protection and source-channel decoding of CELP speech","year":2002,"lang":"en","type":"article","venue":"Electronics Letters","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Code-excited linear prediction; Computer science; Speech recognition; Rayleigh fading; Vector sum excited linear prediction; Residual; Redundancy (engineering); Decoding methods; Speech coding; Algorithm; Linear predictive coding; Fading","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":[0.0001629297,0.0001267895,0.0001432083,0.0001349938,0.0001078472,0.00004144767,0.0004313812,0.00004943239,0.000009326463],"category_scores_gemma":[0.00003426567,0.000126324,0.00003410529,0.0002472564,0.00004667475,0.0004338647,0.0002062653,0.0002402517,0.000006158728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006462729,"about_ca_system_score_gemma":0.000008872898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001006354,"about_ca_topic_score_gemma":0.000002923063,"domain_scores_codex":[0.9988848,0.00005194266,0.0001994313,0.0003300082,0.0002075662,0.0003262388],"domain_scores_gemma":[0.9993353,0.00004165605,0.0001365712,0.000408678,0.00002782733,0.00004992255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001496065,0.00009315133,0.00007055448,0.00005405919,0.00002787608,0.00001405898,0.0009347403,0.0007527585,0.5768084,0.006207144,0.005470371,0.4095519],"study_design_scores_gemma":[0.0004614897,0.0003289767,0.00004817517,0.00007022954,0.000008650825,0.00008224268,0.00001883656,0.3990172,0.5799106,0.00487971,0.01473027,0.0004435835],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07094914,0.0003793202,0.9258459,0.002260754,0.00005764321,0.0001995937,0.000001174468,0.0002464287,0.0000600909],"genre_scores_gemma":[0.9143962,0.0001043982,0.08472917,0.0006014605,0.00004464414,0.00003007713,0.000001606958,0.00001860087,0.00007379438],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8434471,"threshold_uncertainty_score":0.5151341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0254239992686265,"score_gpt":0.2407280993123273,"score_spread":0.2153041000437008,"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."}}