{"id":"W2125199437","doi":"10.1109/mwscas.2007.4488548","title":"A formant frequency estimation algorithm for speech signals with low signal-to-noise ratio","year":2007,"lang":"en","type":"article","venue":"Conference proceedings","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Formant; Cepstrum; Speech recognition; Computer science; Autocorrelation; Vocal tract; Impulse response; Autoregressive model; Noise (video); Speech processing; Signal-to-noise ratio (imaging); Algorithm; Mathematics; Artificial intelligence; Statistics; 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":[0.0007185408,0.000264946,0.0002550963,0.0002490545,0.0002700818,0.0007449411,0.0007658812,0.00009289916,0.00002118358],"category_scores_gemma":[0.00008635156,0.0002221772,0.0000504116,0.0006950772,0.00005305676,0.001814311,0.00009748097,0.000149036,0.00004562589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007746241,"about_ca_system_score_gemma":0.0002737448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008425582,"about_ca_topic_score_gemma":0.000004616131,"domain_scores_codex":[0.9979569,0.000003197952,0.0003716093,0.0005800771,0.0004435701,0.0006446452],"domain_scores_gemma":[0.9982439,0.0000657653,0.0002216335,0.000159525,0.001035474,0.0002737342],"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":[0.00002588223,0.00006263908,0.0003403216,0.0001130108,0.00001557769,0.00001041775,0.002120072,0.00001721297,0.09266362,0.003928932,0.0003805066,0.9003218],"study_design_scores_gemma":[0.0006100642,0.0005373929,0.0003628562,0.0003144104,0.00001487919,0.00006303722,0.0002177246,0.2086043,0.7739053,0.01474048,0.0001765296,0.0004530569],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03801857,0.00003235373,0.9583528,0.0006080972,0.0000784596,0.0007306896,0.000003352367,0.0002702409,0.001905425],"genre_scores_gemma":[0.4590023,0.000001736212,0.5403118,0.0003939642,0.00007987491,0.00006389363,0.000003485609,0.0000129458,0.0001299874],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8998687,"threshold_uncertainty_score":0.9060122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01668165069741968,"score_gpt":0.25972919146413,"score_spread":0.2430475407667104,"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."}}