{"id":"W4366779161","doi":"10.1016/j.specom.2023.04.003","title":"Comparative analysis of various feature extraction techniques for classification of speech disfluencies","year":2023,"lang":"en","type":"article","venue":"Speech Communication","topic":"Stuttering Research and Treatment","field":"Psychology","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"CSIR-Central Scientific Instruments Organisation; Academy of Scientific and Innovative Research; Queen's University","keywords":"Computer science; Speech recognition; Mel-frequency cepstrum; Spectrogram; Feature extraction; Phrase; Linear prediction; Classifier (UML); Artificial intelligence; Speech processing; Linear predictive coding; Cepstrum; Natural language processing","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001489309,0.0007149915,0.0008588441,0.001995246,0.0003074264,0.0008275959,0.0003638019,0.0004943105,0.001906301],"category_scores_gemma":[0.003073712,0.0001306201,0.0009544475,0.001438468,0.0001758471,0.0007865502,0.0003062945,0.0004257748,0.0005304769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001946767,"about_ca_system_score_gemma":0.0003886344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002359119,"about_ca_topic_score_gemma":0.002208106,"domain_scores_codex":[0.9994352,0.0001085872,0.00008611561,0.0001193683,0.0001406269,0.0001100326],"domain_scores_gemma":[0.9972522,0.001851795,0.0001138083,0.00009139044,0.0006427703,0.00004808077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00199064,0.000264132,0.009749277,0.0005027195,0.0002888373,0.000134279,0.0001848569,0.004445999,0.1057603,0.0003229667,0.001219307,0.8751366],"study_design_scores_gemma":[0.0002950931,0.004638969,0.3857629,0.0002684361,0.002473789,0.001942679,0.001344129,0.3491689,0.2435557,0.001537176,0.008770163,0.0002420588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7086526,0.006993659,0.2772272,0.0002581166,0.0002600889,0.0002105208,0.001514998,0.00174643,0.003136436],"genre_scores_gemma":[0.87664,0.002678705,0.1151507,0.00005745105,0.0001166057,0.0001785775,0.002881063,0.0001752628,0.002121541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002359119,"threshold_uncertainty_score":0.007876337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1014111182220048,"score_gpt":0.4468027347937438,"score_spread":0.345391616571739,"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."}}