{"id":"W3138474741","doi":"10.1121/10.0005482","title":"Learning spectro-temporal representations of complex sounds with parameterized neural networks","year":2021,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Centre National de la Recherche Scientifique; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales; Institut national de recherche en informatique et en automatique (INRIA); Canadian Institute for Advanced Research","keywords":"Interpretability; Zebra finch; Computer science; Auditory cortex; Speech recognition; Artificial neural network; Task (project management); Variety (cybernetics); Layer (electronics); Artificial intelligence; Parameterized complexity; Pattern recognition (psychology); Psychology; Neuroscience","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004551584,0.0008482186,0.0003024585,0.000386472,0.0001358411,0.0007748174,0.0006711521,0.0006039767,0.001467948],"category_scores_gemma":[0.001992521,0.0003880715,0.0006279441,0.0004157365,0.0003605144,0.001320077,0.0004922886,0.001344536,0.0004999502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007628818,"about_ca_system_score_gemma":0.000471056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004337068,"about_ca_topic_score_gemma":0.006785756,"domain_scores_codex":[0.9998723,0.00002946703,0.000007423559,0.00004980941,0.0000216148,0.00001940578],"domain_scores_gemma":[0.9994938,0.0002729355,0.0000753065,0.00007953306,0.00005892577,0.00001936923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000964719,0.00005769001,0.001357906,0.00005446781,0.00008709627,0.00003636777,0.0000436576,0.8907859,0.0163734,0.003659904,0.0007912057,0.08665592],"study_design_scores_gemma":[0.000001366748,0.000006140563,0.0002158884,0.000002440426,0.000004200235,0.000004990591,0.000003240034,0.9971489,0.000877837,0.001603533,0.0001284177,0.00000300994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06921034,0.0003511103,0.9277185,0.0001889826,0.00004234337,0.00002261328,0.0003170395,0.001142087,0.001006956],"genre_scores_gemma":[0.8785138,0.0003386218,0.1175898,0.0001089541,0.00004000491,0.00007399647,0.0007051055,0.0001776333,0.002452056],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004337068,"threshold_uncertainty_score":0.00862366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01895201292049181,"score_gpt":0.2681138867574825,"score_spread":0.2491618738369907,"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."}}