{"id":"W2766944760","doi":"10.48550/arxiv.1711.00333","title":"An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Keyword spotting; Computer science; Proxy (statistics); Convolutional neural network; Predictive power; Inference; Spotting; Artificial intelligence; Footprint; Artificial neural network; Data mining; Machine learning; Geography","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":[0.0005701921,0.0007788408,0.0003794804,0.0004109423,0.0003058229,0.000480479,0.001030635,0.0004298298,0.004068101],"category_scores_gemma":[0.004467888,0.0002121692,0.0002268443,0.0006389015,0.0003837953,0.001328257,0.0003491311,0.0006767858,0.0006529743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008892399,"about_ca_system_score_gemma":0.0004854267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004791005,"about_ca_topic_score_gemma":0.006475412,"domain_scores_codex":[0.9995328,0.00008322594,0.00004356311,0.0001035961,0.0001368883,0.00009986551],"domain_scores_gemma":[0.997827,0.001297676,0.0001330191,0.0002936129,0.0003772214,0.00007148428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005284719,0.001061113,0.01323579,0.001140842,0.0003285728,0.0008854265,0.0003383786,0.4915375,0.1428311,0.005043943,0.01200663,0.326306],"study_design_scores_gemma":[0.0000875845,0.0008514265,0.005862815,0.00003168258,0.00008268699,0.0002084754,0.0001334571,0.8903227,0.09754238,0.002057074,0.002792178,0.00002757385],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9680892,0.0005728142,0.02293371,0.0003489665,0.0001156572,0.00005972818,0.0007856555,0.001787456,0.005306888],"genre_scores_gemma":[0.9927425,0.0001459894,0.004990989,0.00004281679,0.00001019944,0.00003476117,0.0004404177,0.000100664,0.001491571],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004791005,"threshold_uncertainty_score":0.01360917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1042287017111895,"score_gpt":0.2376853763106874,"score_spread":0.1334566745994978,"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."}}