{"id":"W4407901593","doi":"10.1109/ictis62692.2024.10894239","title":"Transfer Learning-Based Deep Residual Learning for Speech Recognition in Clean and Noisy Environments","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Transfer of learning; Residual; Deep learning; Artificial intelligence; Speech recognition; Algorithm","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006185472,0.000290251,0.0002869911,0.0003039101,0.0001276584,0.0004677732,0.0003613458,0.0002808053,0.00003288819],"category_scores_gemma":[0.00007697767,0.0002900269,0.00009017632,0.0001576888,0.00004548434,0.0002232542,0.0004122805,0.00121975,0.00004795048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008539636,"about_ca_system_score_gemma":0.0001035704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003143434,"about_ca_topic_score_gemma":0.00008399785,"domain_scores_codex":[0.9979324,0.0001045708,0.0003427815,0.0009658175,0.0002758598,0.0003785921],"domain_scores_gemma":[0.9994686,0.0001464556,0.00005878575,0.0002122107,0.00002194656,0.00009196938],"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":[0.00003739557,0.0000523261,0.0005384723,0.0004988464,0.0000241378,0.00004265109,0.000593694,0.0137424,0.002826334,0.00002921454,0.00004900658,0.9815655],"study_design_scores_gemma":[0.002328365,0.0005641493,0.001176079,0.001564951,0.0000960309,0.00002948974,0.000432763,0.392737,0.5589831,0.03510923,0.005387008,0.001591784],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3473792,0.0005074883,0.648609,0.001322628,0.000298574,0.0005425846,0.00000447835,0.0002962424,0.001039788],"genre_scores_gemma":[0.8648283,0.0001198333,0.1326483,0.0004264677,0.0001944855,0.0001251055,0.0001291971,0.00006449823,0.001463833],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9799737,"threshold_uncertainty_score":0.9999552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02214007469954428,"score_gpt":0.2505423248597058,"score_spread":0.2284022501601616,"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."}}