{"id":"W2981902467","doi":"10.1109/icassp40776.2020.9053893","title":"Detecting Multiple Speech Disfluencies Using a Deep Residual Network with Bidirectional Long Short-Term Memory","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Stuttering Research and Treatment","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Speech recognition; Stuttering; Term (time); Residual; Identification (biology); Long short term memory; Artificial intelligence; Natural language processing; Recurrent neural network; Linguistics; Artificial neural network; Algorithm","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":[0.0005222858,0.001057267,0.000500463,0.000485837,0.0002482573,0.0004699729,0.0008255627,0.000597836,0.001419859],"category_scores_gemma":[0.001346862,0.0003135692,0.0004882616,0.0002344843,0.0002923166,0.0007024743,0.0008980241,0.0008911323,0.0005614549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000401485,"about_ca_system_score_gemma":0.0006183809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006521918,"about_ca_topic_score_gemma":0.01091958,"domain_scores_codex":[0.9997932,0.00004240502,0.00001240312,0.00006975694,0.00003551969,0.00004673056],"domain_scores_gemma":[0.9996164,0.0001593145,0.00005488813,0.00004154743,0.00008738786,0.00004041743],"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":[0.001837435,0.0009035706,0.0277008,0.0003076794,0.0004477802,0.0009849507,0.0004778634,0.1316832,0.08855218,0.002418956,0.007773039,0.7369126],"study_design_scores_gemma":[0.00002586353,0.000351262,0.006562026,0.00004138482,0.0001291627,0.0002156317,0.0001070725,0.9740068,0.01493688,0.002644123,0.0009457431,0.00003403041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6539068,0.002135141,0.3309985,0.001076401,0.0002140904,0.000113633,0.001121833,0.00406742,0.006366305],"genre_scores_gemma":[0.967654,0.0002951049,0.02769827,0.0001578196,0.00002577652,0.00004900707,0.0007964298,0.00004705393,0.003276626],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006521918,"threshold_uncertainty_score":0.01296788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0919732790496448,"score_gpt":0.3544207328914402,"score_spread":0.2624474538417954,"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."}}