{"id":"W2286669694","doi":"10.1109/globalsip.2015.7418378","title":"Unsupervised keyword spotting using bounded generalized Gaussian mixture model with ICA","year":2015,"lang":"en","type":"article","venue":"","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Keyword spotting; Computer science; Artificial intelligence; TIMIT; Speech recognition; Independent component analysis; Pattern recognition (psychology); Dynamic time warping; Mixture model; Spotting; Hidden Markov model","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007081071,0.001209869,0.001041088,0.001069285,0.0003291354,0.0006566015,0.0009970152,0.0009119157,0.0009828635],"category_scores_gemma":[0.001926042,0.0003846802,0.001222009,0.001160142,0.0006790452,0.001377758,0.0008591744,0.001166025,0.001195964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003352635,"about_ca_system_score_gemma":0.00071916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002226029,"about_ca_topic_score_gemma":0.00238191,"domain_scores_codex":[0.9992151,0.000226029,0.00003560817,0.0001975872,0.0002688326,0.00005675617],"domain_scores_gemma":[0.9993319,0.0002951027,0.00006807127,0.0001307025,0.000149025,0.00002518998],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000572286,0.0001259265,0.001151182,0.0003025123,0.0002536034,0.0003507116,0.0002557214,0.1642435,0.1422501,0.01121294,0.003146888,0.6761346],"study_design_scores_gemma":[0.00001676854,0.00007222258,0.0008764669,0.00001303273,0.00003624086,0.0003224852,0.00003271027,0.9550391,0.03544993,0.005261252,0.002838805,0.00004106854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005140883,0.0001798984,0.9933593,0.00003488904,0.00002240242,0.00001785508,0.00003632858,0.0007632076,0.0004452048],"genre_scores_gemma":[0.1925004,0.0006111239,0.8025228,0.0001138832,0.00009804752,0.0001182106,0.0006019606,0.0003574025,0.003076181],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002226029,"threshold_uncertainty_score":0.004426181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06565962370306201,"score_gpt":0.2900633329861301,"score_spread":0.2244037092830681,"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."}}