{"id":"W4312353038","doi":"10.1109/ijcnn55064.2022.9892285","title":"Named Entity Recognition for Audio De-Identification","year":2022,"lang":"en","type":"article","venue":"2022 International Joint Conference on Neural Networks (IJCNN)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs","keywords":"Pipeline (software); Computer science; Task (project management); Named-entity recognition; Speech recognition; Identification (biology); Natural language processing; Audio mining; Artificial intelligence; Acoustic model; Speech processing; Programming language","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":[0.003017958,0.001377488,0.0009122369,0.003307342,0.001160804,0.001582195,0.001707073,0.001318122,0.00810804],"category_scores_gemma":[0.008510816,0.000384707,0.001168838,0.002709282,0.0005669335,0.004237168,0.001961462,0.001483993,0.009284289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007884038,"about_ca_system_score_gemma":0.001124252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004376341,"about_ca_topic_score_gemma":0.005766391,"domain_scores_codex":[0.9963287,0.001047908,0.0003416842,0.00129734,0.0007811256,0.0002032818],"domain_scores_gemma":[0.9948223,0.001654947,0.0004761971,0.001825376,0.001120225,0.0001010112],"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":[0.0003943908,0.0001413772,0.002664205,0.0007968777,0.0001695832,0.0004793048,0.000398371,0.008874414,0.05323664,0.01085063,0.04746371,0.8745304],"study_design_scores_gemma":[0.00007511585,0.0002786324,0.01239084,0.0003358049,0.0002920815,0.002222844,0.001053569,0.3588052,0.2131488,0.05282981,0.3582981,0.0002691803],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01504971,0.002953917,0.9332784,0.0008051882,0.0005163353,0.0003826608,0.01038664,0.02895049,0.007676499],"genre_scores_gemma":[0.1579717,0.001833861,0.7848202,0.0003955349,0.0002452784,0.0004775786,0.04310061,0.0007870728,0.01036817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00810804,"threshold_uncertainty_score":0.02712411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04035002746334673,"score_gpt":0.2873490868881336,"score_spread":0.2469990594247869,"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."}}