{"id":"W4226435591","doi":"10.3758/s13428-022-02029-6","title":"Shennong: A Python toolbox for audio speech features extraction","year":2023,"lang":"en","type":"preprint","venue":"Behavior Research Methods","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Agence Nationale de la Recherche; Institut national de recherche en informatique et en automatique (INRIA); Canadian Institute for Advanced Research; Facebook","keywords":"Computer science; Python (programming language); Speech recognition; Toolbox; Normalization (sociology); Software; Scripting language; Mel-frequency cepstrum; Speech processing; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Feature extraction; Programming language","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01680961,0.0005055923,0.0006870389,0.001290686,0.0007346637,0.002109948,0.003409195,0.0008268071,0.00003255126],"category_scores_gemma":[0.002732071,0.0004887731,0.0004667741,0.001446939,0.0001966139,0.0005971703,0.00294486,0.003265622,0.00008845948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004719244,"about_ca_system_score_gemma":0.001143022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002455358,"about_ca_topic_score_gemma":0.00004339414,"domain_scores_codex":[0.9921306,0.001926893,0.0006463379,0.002040308,0.001715742,0.001540099],"domain_scores_gemma":[0.9936434,0.002249064,0.0002933099,0.002191597,0.001214248,0.0004084047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004151991,0.0001783822,0.0002292898,0.0003659393,0.00003480497,0.0002048227,0.0004409161,0.00002052914,0.06622407,0.0004739895,0.01258565,0.9192001],"study_design_scores_gemma":[0.0008677387,0.0004283481,0.01741718,0.0007357719,0.0001014069,0.0002176839,0.000330769,0.002445356,0.8618824,0.07785796,0.03623515,0.00148026],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006964389,0.001051125,0.9815788,0.002058475,0.00347356,0.002678493,0.00004589742,0.00112635,0.001022938],"genre_scores_gemma":[0.001838571,0.0001530223,0.9804587,0.00005135575,0.0009346813,0.00297651,0.00006354227,0.0001312735,0.01339237],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9177198,"threshold_uncertainty_score":0.9997564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4835932963510312,"score_gpt":0.6236894237901746,"score_spread":0.1400961274391433,"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."}}