{"id":"W2085830557","doi":"10.1007/s10772-009-9025-9","title":"A noise-robust front-end for distributed speech recognition in mobile communications","year":2007,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Front and back ends; Formant; Mel-frequency cepstrum; GSM; Speech processing; Cepstrum; Noise (video); Task (project management); Artificial intelligence; Feature extraction; Telecommunications","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":[0.0009784137,0.000125606,0.0002240349,0.001131867,0.00007061364,0.0001009005,0.002636774,0.0001811855,0.00002335919],"category_scores_gemma":[0.0004036686,0.0001239397,0.0001001724,0.0005149069,0.0001311123,0.0006430299,0.0003118519,0.000444137,0.00001840441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002800936,"about_ca_system_score_gemma":0.0001178464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001214093,"about_ca_topic_score_gemma":0.0001514704,"domain_scores_codex":[0.9984379,0.00001976218,0.0007086261,0.0001968709,0.0003530354,0.0002838098],"domain_scores_gemma":[0.9977721,0.0002104953,0.0005413421,0.0003738806,0.001041169,0.00006104348],"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":[0.00005627302,0.0001838109,0.002087892,0.000004965258,0.00004774866,0.0001554763,0.00007731113,0.00002594408,0.01245676,0.0005478512,0.0003701191,0.9839858],"study_design_scores_gemma":[0.004065647,0.0006125534,0.003050861,0.0004057752,0.0000279009,0.003770971,0.0007781519,0.002952202,0.8012758,0.1208937,0.06168814,0.0004783451],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2176394,0.0008595312,0.7684876,0.01130184,0.0008529912,0.0002478095,0.00003769718,0.0001088037,0.000464276],"genre_scores_gemma":[0.4639674,0.0001498496,0.5354713,0.0001704409,0.0001676499,0.00001342925,0.00002280025,0.000009461645,0.00002763141],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9835075,"threshold_uncertainty_score":0.5054114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02978584671247504,"score_gpt":0.3092272312638119,"score_spread":0.2794413845513368,"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."}}