{"id":"W4236889828","doi":"10.22215/etd/2017-12205","title":"Monaural Music Separation via Supervised Non-Negative Matrix Factor with Side-Information","year":2017,"lang":"en","type":"dissertation","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Monaural; Spectrogram; Source separation; Computer science; Template; Non-negative matrix factorization; Speech recognition; Offset (computer science); Algorithm; Matrix (chemical analysis); Pattern recognition (psychology); Artificial intelligence; Matrix decomposition","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":[0.0009537321,0.001246213,0.001063943,0.0005803151,0.0004662821,0.000627024,0.0008367036,0.0007436355,0.002156951],"category_scores_gemma":[0.002156178,0.0003602222,0.001259653,0.0006793157,0.0006206012,0.001202605,0.0008162156,0.001547375,0.001615348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003287557,"about_ca_system_score_gemma":0.001080162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001458227,"about_ca_topic_score_gemma":0.003686723,"domain_scores_codex":[0.9993466,0.0001612632,0.00003285142,0.0001992387,0.0002019255,0.00005812914],"domain_scores_gemma":[0.999256,0.0002586238,0.00008910547,0.0001246655,0.0002344634,0.00003716935],"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":[0.0004177979,0.0002138309,0.0009491015,0.000337939,0.0001566106,0.0001507379,0.0001752796,0.1335002,0.06526522,0.02497196,0.007367959,0.7664934],"study_design_scores_gemma":[0.00002309853,0.00009597185,0.0004565319,0.00001988806,0.00003000047,0.0001419983,0.00002529087,0.9717374,0.01323188,0.009196079,0.005017526,0.00002437417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003990785,0.0002788974,0.9945877,0.00005420428,0.00005037474,0.00002270851,0.00004514051,0.000279059,0.0006911354],"genre_scores_gemma":[0.1159081,0.000715038,0.875682,0.0001476362,0.000218826,0.0001316857,0.0006744096,0.0001961648,0.006326059],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002156951,"threshold_uncertainty_score":0.007215679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01318851839047365,"score_gpt":0.2870312074980628,"score_spread":0.2738426891075892,"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."}}