{"id":"W4238241308","doi":"10.22215/etd/2015-11298","title":"Variable Length Windowing to Improve Non-Negative Matrix Factorization of Music Signals","year":2015,"lang":"en","type":"dissertation","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Short-time Fourier transform; Non-negative matrix factorization; SIGNAL (programming language); Computer science; Pattern recognition (psychology); Matrix decomposition; Algorithm; Artificial intelligence; Time–frequency analysis; Window function; Speech recognition; Dimension (graph theory); Fourier transform; Mathematics; Divergence (linguistics); Variable (mathematics); Frame (networking); Fourier analysis; Computer vision; Filter (signal processing)","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":[0.0008567827,0.001011249,0.000611354,0.0006147941,0.0003130136,0.000520826,0.0005722819,0.0005830592,0.002962508],"category_scores_gemma":[0.00367075,0.0002907426,0.0006551504,0.0008098049,0.0003763916,0.001471585,0.0005697639,0.001112319,0.001196372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002650602,"about_ca_system_score_gemma":0.0004954753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001610272,"about_ca_topic_score_gemma":0.003291215,"domain_scores_codex":[0.9995701,0.00008221987,0.00003414632,0.0001107338,0.0001655532,0.00003722623],"domain_scores_gemma":[0.9988397,0.0005983006,0.00009031063,0.0001653351,0.0002665854,0.00003990074],"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":[0.0003819235,0.0001939082,0.0008247267,0.000266695,0.00008195039,0.0001923737,0.000229095,0.0866235,0.2271164,0.02006139,0.004464523,0.6595635],"study_design_scores_gemma":[0.00002851,0.0002212769,0.001624736,0.0000299937,0.00004920086,0.0001545658,0.00004372453,0.916492,0.06405406,0.007466394,0.009803683,0.00003184569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01495393,0.0005540064,0.9827964,0.00007656478,0.0000941868,0.00003321605,0.00006070998,0.0005048733,0.0009260316],"genre_scores_gemma":[0.1384968,0.001133044,0.8550568,0.0001003163,0.0001455863,0.0001093008,0.0005354179,0.0003164297,0.00410627],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002962508,"threshold_uncertainty_score":0.009910524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01757714058288126,"score_gpt":0.2852536470239959,"score_spread":0.2676765064411147,"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."}}