{"id":"W3169359258","doi":"","title":"Study of the Non-negative Matrix Factorization behavior to estimate the urban traffic sound levels","year":2019,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Non-negative matrix factorization; Computer science; Noise (video); Matrix decomposition; Sound (geography); Traffic noise; Mixing (physics); Matrix (chemical analysis); Source separation; Artificial intelligence; Speech recognition; Acoustics; Image (mathematics); Noise reduction","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002721368,0.0003142001,0.0003475561,0.0001386815,0.0005224491,0.0007811037,0.004143881,0.0001491515,0.0000119093],"category_scores_gemma":[0.0008030013,0.0002207527,0.0001577659,0.0008202576,0.0001234387,0.0002332948,0.002909737,0.0005582242,0.00002350766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001145845,"about_ca_system_score_gemma":0.0003700523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002255183,"about_ca_topic_score_gemma":0.0007269896,"domain_scores_codex":[0.9953169,0.002383208,0.0005348662,0.0007564389,0.0006958761,0.0003127727],"domain_scores_gemma":[0.9935485,0.0008751274,0.0007514132,0.00313828,0.001586096,0.000100562],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003705568,0.007111683,0.1007738,0.0006336517,0.0004720127,0.00001453478,0.6425157,0.04842188,0.01799608,0.01500332,0.002067966,0.1649523],"study_design_scores_gemma":[0.002444097,0.0000117781,0.4082192,0.003815022,0.0003591667,0.00002484971,0.002897759,0.07731696,0.4963839,0.005805518,0.0008417169,0.001879956],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6537494,0.00007798366,0.3411548,0.002141037,0.0004404807,0.001347572,0.00002218594,0.00009973679,0.0009667643],"genre_scores_gemma":[0.969027,0.000005235544,0.02875186,0.00004826655,0.00001844386,0.0001166997,0.00001409704,0.00002696126,0.001991471],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6396179,"threshold_uncertainty_score":0.9002033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02437047376377993,"score_gpt":0.294798704552846,"score_spread":0.270428230789066,"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."}}