{"id":"W3106918760","doi":"10.1109/ccece47787.2020.9255693","title":"Low-Power Low-Cost Audio Front-End for Keyword Spotting","year":2020,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Keyword spotting; Idle; Spotting; Computer science; Power consumption; Power (physics); Front and back ends; State (computer science); Real-time computing; Embedded system; Speech recognition; Operating system; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0001665906,0.0001575227,0.0001856654,0.0000386083,0.0001818424,0.0003378859,0.0007561062,0.00005568438,0.0002190597],"category_scores_gemma":[0.0001539205,0.0001371722,0.00009686133,0.0002333515,0.00002533424,0.0006140743,0.0002152951,0.0001192948,0.0003208742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002650453,"about_ca_system_score_gemma":0.00009311748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003583707,"about_ca_topic_score_gemma":0.000003718886,"domain_scores_codex":[0.9986141,0.00001326169,0.0002284293,0.0004896533,0.0002173758,0.0004371319],"domain_scores_gemma":[0.9992641,0.00008610728,0.0000858071,0.0002686173,0.00008212891,0.0002132186],"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":[0.00007459719,0.0001586712,0.002067786,0.0002973057,0.00006316429,0.0000786264,0.004481406,0.000229991,0.04211279,0.003995647,0.09961777,0.8468223],"study_design_scores_gemma":[0.001515502,0.0001658367,0.0008491866,0.0001291914,0.00001156767,0.00001265997,0.0002117963,0.03958187,0.8765396,0.002059638,0.0781805,0.0007426194],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01432264,0.00009041193,0.9631134,0.007141646,0.0003478416,0.0002522585,0.000002829433,0.0003913434,0.01433763],"genre_scores_gemma":[0.6605766,0.000003828871,0.3276218,0.009989068,0.0003454663,0.00002685454,0.000003460495,0.00002122961,0.001411749],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8460796,"threshold_uncertainty_score":0.5593718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01943909415295511,"score_gpt":0.2446014331631386,"score_spread":0.2251623390101835,"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."}}