{"id":"W4288091411","doi":"10.48550/arxiv.1910.12590","title":"Detecting Multiple Speech Disfluencies using a Deep Residual Network\\n with Bidirectional Long Short-Term Memory","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stuttering Research and Treatment","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Speech recognition; Computer science; Residual; Stuttering; Term (time); Identification (biology); Long short term memory; Artificial intelligence; Natural language processing; Linguistics; Recurrent neural network; Artificial neural network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002247483,0.0004452685,0.0004401304,0.0002939777,0.0003396421,0.00008961172,0.0004758745,0.0003282598,0.0003467647],"category_scores_gemma":[0.00003293767,0.0004467499,0.0001926957,0.00039755,0.0002052877,0.0001254847,0.0007720846,0.0008404018,0.000148361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005448568,"about_ca_system_score_gemma":0.000189924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001352797,"about_ca_topic_score_gemma":0.001738441,"domain_scores_codex":[0.9972781,0.0002376473,0.0002128904,0.001250549,0.0001891807,0.0008316318],"domain_scores_gemma":[0.9982198,0.000342386,0.000166899,0.000914195,0.0001497931,0.000206923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006885729,0.0001505548,0.7869298,0.00007233019,0.0009019751,0.002874248,0.0003399369,0.2065896,0.00005477343,0.0001109415,0.00005112607,0.001236121],"study_design_scores_gemma":[0.002870464,0.0004720595,0.9510889,0.0005645754,0.0006356809,0.0003154103,0.001352454,0.04016834,0.0005449936,0.0005972429,0.00005083104,0.001339041],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.981251,0.0002694348,0.01353615,0.00000977472,0.0008776353,0.0006626107,0.00002827603,0.0001832243,0.003181886],"genre_scores_gemma":[0.9962648,0.00003298045,0.000643833,0.00001729194,0.0004365638,0.000005507679,0.00003599095,0.00006574664,0.002497341],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1664212,"threshold_uncertainty_score":0.9997984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1201131839651647,"score_gpt":0.2539747729136482,"score_spread":0.1338615889484835,"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."}}