{"id":"W3198298452","doi":"10.1109/taslp.2021.3110146","title":"FluentNet: End-to-End Detection of Stuttered Speech Disfluencies With Deep Learning","year":2021,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Stuttering Research and Treatment","field":"Psychology","cited_by":103,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Benchmark (surveying); Speech recognition; Stuttering; Deep learning; Field (mathematics); Convolutional neural network; Artificial neural network; Artificial intelligence; End-to-end principle; Psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006434547,0.002432216,0.0008208163,0.0009441593,0.0005048773,0.0007311867,0.001956666,0.001581349,0.003895464],"category_scores_gemma":[0.002041152,0.0006186821,0.000847269,0.0004576849,0.0004147473,0.001256818,0.001399859,0.001502461,0.002215324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001002311,"about_ca_system_score_gemma":0.001163873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02187407,"about_ca_topic_score_gemma":0.04147362,"domain_scores_codex":[0.999613,0.00005792596,0.00002740483,0.0001529751,0.00007596796,0.00007267165],"domain_scores_gemma":[0.9996152,0.0001417161,0.00003073801,0.00007678448,0.00009993347,0.00003554529],"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":[0.001783134,0.001168278,0.01082317,0.0009189553,0.000593976,0.001522966,0.0003830823,0.1078122,0.03526479,0.001927943,0.1938315,0.64397],"study_design_scores_gemma":[0.0001706665,0.0005600231,0.006162676,0.0001406259,0.0001236992,0.0005936985,0.0001973135,0.9371083,0.03204457,0.004550593,0.01823743,0.0001102807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.439793,0.007951256,0.3588383,0.001917469,0.001496768,0.001152151,0.05163391,0.1176379,0.01957918],"genre_scores_gemma":[0.6920898,0.001119834,0.1732063,0.001611226,0.0001632785,0.0009981709,0.1068069,0.001538411,0.02246615],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02187407,"threshold_uncertainty_score":0.04349351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0163548071643285,"score_gpt":0.3020243447461965,"score_spread":0.285669537581868,"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."}}