{"id":"W2950689855","doi":"10.48550/arxiv.1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Recurrent neural network; Computer science; Connectionism; TIMIT; Speech recognition; Artificial intelligence; Context (archaeology); Deep learning; Benchmark (surveying); Time delay neural network; Artificial neural network; Hidden Markov model","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":[0.0001883171,0.0004026408,0.0003631021,0.0002933565,0.0001631226,0.0002991146,0.00132275,0.0003351163,0.0003579519],"category_scores_gemma":[0.00002853705,0.0004000532,0.0002083439,0.0005925998,0.0001006381,0.0006129749,0.0008721314,0.0007636959,0.0004432918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001651649,"about_ca_system_score_gemma":0.00007334226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001080566,"about_ca_topic_score_gemma":0.00009321987,"domain_scores_codex":[0.9977536,0.0002172319,0.0002237934,0.001215769,0.0001318328,0.0004578278],"domain_scores_gemma":[0.997964,0.0001373935,0.0002996354,0.001001965,0.0003317246,0.0002652914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009585132,0.0003336389,0.00123356,0.00009570048,0.000249298,0.001159529,0.0001597695,0.04060595,0.000006315225,0.005955501,0.001300187,0.9488047],"study_design_scores_gemma":[0.0004000606,0.00009233726,0.0006334358,0.0001297305,0.00007935771,0.00004322558,0.00004577823,0.9866071,0.0001141082,0.01101387,0.0002165942,0.0006244177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2434398,0.00005861395,0.7488111,0.0001598578,0.0009967928,0.0005098666,0.000009346741,0.0004707569,0.005543856],"genre_scores_gemma":[0.9814563,0.0002691118,0.01720283,0.0002530258,0.0001781773,0.00000548456,0.00005409733,0.00002919015,0.0005518174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9481803,"threshold_uncertainty_score":0.9998451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0770478288527954,"score_gpt":0.1795214216656187,"score_spread":0.1024735928128233,"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."}}