{"id":"W2964187693","doi":"10.1109/icassp.2018.8462688","title":"Deep Residual Learning for Small-Footprint Keyword Spotting","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Keyword spotting; Computer science; Residual; Convolutional neural network; Deep learning; Footprint; Memory footprint; Benchmark (surveying); Artificial intelligence; Spotting; Machine learning; Speech recognition; Algorithm; Cartography","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":[0.0009271089,0.001211597,0.0009383426,0.0006293041,0.0002485496,0.0008805081,0.001594987,0.0009658507,0.005116117],"category_scores_gemma":[0.004365517,0.0002782261,0.0005212247,0.0006650115,0.0004252594,0.00194544,0.001230091,0.001292604,0.002987074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005349763,"about_ca_system_score_gemma":0.0009005874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006148698,"about_ca_topic_score_gemma":0.01027691,"domain_scores_codex":[0.999527,0.00008669947,0.00002923707,0.0001519435,0.0001301785,0.00007502254],"domain_scores_gemma":[0.9990049,0.0004624407,0.0000688508,0.0001983299,0.0001919199,0.00007357394],"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":[0.001412513,0.0003713434,0.001429065,0.0004720921,0.0001503538,0.0003329726,0.0001600933,0.1711189,0.08666302,0.003891754,0.01325699,0.7207408],"study_design_scores_gemma":[0.00004602599,0.0002160127,0.0003663996,0.00001519379,0.00002649989,0.00009647236,0.00004790772,0.9521105,0.04153012,0.002597784,0.002926918,0.00002015509],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1465676,0.002288071,0.8134872,0.0005081226,0.0002911112,0.0001431439,0.001714618,0.02908599,0.005914182],"genre_scores_gemma":[0.6420081,0.0006181247,0.3420345,0.0003306093,0.0001186333,0.0001209962,0.003618007,0.001109143,0.01004193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006148698,"threshold_uncertainty_score":0.01711506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04154259823274774,"score_gpt":0.2640082849263389,"score_spread":0.2224656866935912,"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."}}