{"id":"W2168186580","doi":"10.1109/isspa.2003.1224957","title":"Robust formant tracking for continuous speech with speaker variability","year":2003,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Formant; Speech recognition; Computer science; Voice; Noise (video); TIMIT; Background noise; Detector; Speech processing; Speech enhancement; QUIET; Hidden Markov model; Artificial intelligence; 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":[0.0007119762,0.0001283156,0.0001640894,0.00003679315,0.000148244,0.0002617764,0.0003257671,0.00004240248,0.00003988822],"category_scores_gemma":[0.0001253311,0.000089776,0.00004605817,0.0002255201,0.00003007723,0.0006718929,0.00003162926,0.00007844566,0.00001208989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002986169,"about_ca_system_score_gemma":0.00009938536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004937043,"about_ca_topic_score_gemma":0.00001585459,"domain_scores_codex":[0.9988878,0.0000275472,0.0001796967,0.0003647772,0.0001731181,0.0003670263],"domain_scores_gemma":[0.9992262,0.0001109737,0.00006954712,0.0003601457,0.0001507414,0.0000824005],"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":[0.00009410749,0.0006922021,0.02726034,0.0002880299,0.0001122981,0.00009427257,0.001817864,0.0009037087,0.007598141,0.1557703,0.004230891,0.8011379],"study_design_scores_gemma":[0.002369359,0.000437024,0.002232796,0.0000765867,0.00002691361,0.000389422,0.0002443966,0.01375657,0.927301,0.0259871,0.02635412,0.0008247065],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02840168,0.00001980892,0.9356212,0.0002282626,0.0001259613,0.0002449324,6.065058e-7,0.0001674851,0.03519009],"genre_scores_gemma":[0.4342087,6.928871e-7,0.5648527,0.0003057083,0.00002858009,0.000009935944,5.777738e-7,0.000006889024,0.0005862223],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9197029,"threshold_uncertainty_score":0.3660959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02730022147249841,"score_gpt":0.2312653986141371,"score_spread":0.2039651771416387,"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."}}