{"id":"W4388705825","doi":"10.1111/2041-210x.14239","title":"<scp>ECOGEN</scp> : Bird sounds generation using deep learning","year":2023,"lang":"en","type":"article","venue":"Methods in Ecology and Evolution","topic":"Animal Vocal Communication and Behavior","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"Research Committee, Aristotle University of Thessaloniki; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canada Foundation for Innovation","keywords":"Spectrogram; Computer science; Deep learning; Artificial intelligence; Classifier (UML); Citizen science; Robustness (evolution); Machine learning; Bioacoustics; Biology","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":[0.001002873,0.00008599082,0.000104896,0.000107096,0.0002109141,0.00001184838,0.00007947245,0.0002446428,0.000005818561],"category_scores_gemma":[0.00053442,0.00009175282,0.00003321934,0.0002038552,0.00008249946,0.000006693761,0.0001272921,0.0001600599,0.00001530109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003494704,"about_ca_system_score_gemma":0.00002733113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002396447,"about_ca_topic_score_gemma":0.0003094425,"domain_scores_codex":[0.9987489,0.0006280775,0.0001685186,0.000219223,0.00003737532,0.0001978989],"domain_scores_gemma":[0.9996555,0.00007458933,0.00006042877,0.0001332184,0.00004006429,0.0000361313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000006147143,0.0000238899,0.2703987,0.000004881563,0.000007921425,0.000001029044,0.00008180467,0.0008596229,0.7210054,0.0001987281,0.00008934425,0.007322532],"study_design_scores_gemma":[0.000375271,0.0002467557,0.9131085,0.000003904952,0.00002574889,0.0000224771,0.0005125183,0.06159873,0.01547417,0.0005684803,0.007971604,0.00009178241],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9289441,0.000486708,0.07002357,0.00003496693,0.000155653,0.00008126946,6.083937e-7,0.00003995241,0.0002332315],"genre_scores_gemma":[0.9549326,0.0002903095,0.04399597,0.00007077983,0.0001006931,0.00002209552,0.00004568744,0.00001529967,0.0005265682],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7055313,"threshold_uncertainty_score":0.3741571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07214148211955569,"score_gpt":0.3935573347401203,"score_spread":0.3214158526205647,"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."}}