{"id":"W2126203737","doi":"10.1109/asru.2009.5372931","title":"Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams","year":2009,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":338,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Keyword spotting; Computer science; Dynamic time warping; Speech recognition; Artificial intelligence; TIMIT; Ranking (information retrieval); Gaussian; Spotting; Viterbi algorithm; Gaussian process; Natural language processing; Pattern recognition (psychology); Hidden Markov model","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":[0.0001670065,0.000184802,0.0001651667,0.00008169989,0.00021441,0.0003258905,0.000638171,0.00005628914,0.0001305653],"category_scores_gemma":[0.000006820252,0.0001498042,0.00006796893,0.0003141466,0.0000225932,0.0004964336,0.0001102308,0.0001350557,0.0002016247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004450377,"about_ca_system_score_gemma":0.00003393682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001618556,"about_ca_topic_score_gemma":0.000001807296,"domain_scores_codex":[0.9986269,0.000028489,0.0002266182,0.0004338815,0.0002942743,0.0003898292],"domain_scores_gemma":[0.9993519,0.00002099375,0.00006794822,0.0003992222,0.00002394937,0.0001360146],"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":[0.00001278925,0.0001069385,0.0004038832,0.000009978906,0.000006526937,0.00005350443,0.0008430248,0.00001508661,0.0173653,0.004660528,0.001039146,0.9754833],"study_design_scores_gemma":[0.009610311,0.005020835,0.1884599,0.001783066,0.00007341475,0.0008897599,0.001122259,0.3188379,0.387555,0.03551821,0.0446414,0.006487994],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3724309,0.00007353419,0.4707178,0.01434033,0.0005382737,0.0002702502,9.033558e-7,0.0008140575,0.1408139],"genre_scores_gemma":[0.945388,0.000002239316,0.04043755,0.01289868,0.0001329272,0.000001685776,0.000002698987,0.000008038758,0.001128185],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9689953,"threshold_uncertainty_score":0.6108839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01218157054232683,"score_gpt":0.2340915820983202,"score_spread":0.2219100115559933,"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."}}