{"id":"W2937708047","doi":"10.1109/mwscas.2018.8623889","title":"Blind Source Separation as Pre-processing to Unsupervised Keyword Spotting via an ICA Mixture Model","year":2018,"lang":"en","type":"article","venue":"","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Keyword spotting; Computer science; Spotting; Speech recognition; Blind signal separation; TIMIT; Preprocessor; Artificial intelligence; Independent component analysis; Speech processing; Pattern recognition (psychology); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006121788,0.0002276983,0.0001854713,0.0002333231,0.0003769751,0.0006858511,0.0009861059,0.0001723628,0.00004565745],"category_scores_gemma":[0.00004862408,0.0002114662,0.0000517642,0.0007429319,0.00004960393,0.001747964,0.0002544048,0.0001927118,0.0001672072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004681031,"about_ca_system_score_gemma":0.0001631165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005100184,"about_ca_topic_score_gemma":0.00005063838,"domain_scores_codex":[0.9980444,0.0001119997,0.0003555492,0.0006863042,0.0004416408,0.0003601304],"domain_scores_gemma":[0.9984804,0.00003000034,0.0001126092,0.0007544152,0.0003819193,0.0002406542],"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":[0.0003234291,0.0006089152,0.000323293,0.00006333936,0.00004035024,0.000007793369,0.1177509,0.04169726,0.1583394,0.0485073,0.008635383,0.6237026],"study_design_scores_gemma":[0.0002190877,0.0002654727,0.00008570655,0.00002180756,0.000004660134,0.00001083714,0.00006003206,0.9357656,0.05430976,0.006253847,0.002710042,0.0002931143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1582145,0.00001001605,0.8291053,0.001379448,0.0000482826,0.0003245129,4.178958e-7,0.001134879,0.009782682],"genre_scores_gemma":[0.6250535,6.579189e-7,0.3686303,0.004105113,0.0001348514,0.00002198399,0.000004526594,0.0000182431,0.00203082],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8940684,"threshold_uncertainty_score":0.8623343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0231757579688052,"score_gpt":0.3341191300906958,"score_spread":0.3109433721218905,"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."}}