{"id":"W4383217247","doi":"10.22541/au.168857312.29438464/v1","title":"Bidirectional Long short-term memory and Recurrent Neural Network model for speech recognition","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Computer science; Recurrent neural network; Speech recognition; Word error rate; Artificial neural network; Long short term memory; Term (time); Short-term memory; Transformer; Artificial intelligence; Language model; Working memory; Cognition","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"],"consensus_categories":[],"category_scores_codex":[0.0006421264,0.0003417039,0.0003740469,0.0002357586,0.000207928,0.0004105416,0.0005081412,0.0002996528,0.00005980419],"category_scores_gemma":[0.00008770191,0.0003368313,0.0002515483,0.0001980049,0.00004561814,0.0002676142,0.0008395224,0.0003964823,0.00005669764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007539598,"about_ca_system_score_gemma":0.0001144419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000166122,"about_ca_topic_score_gemma":0.0001605888,"domain_scores_codex":[0.9976358,0.00008476877,0.0004510137,0.001048523,0.0003558865,0.0004240249],"domain_scores_gemma":[0.9986386,0.0003493018,0.0001279302,0.0004654652,0.0002438597,0.0001748173],"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":[0.0000182084,0.00004746743,0.000212356,0.0001107504,0.00005953391,0.00001277324,0.00006369228,0.001440421,0.00001408135,0.0001068059,0.00959263,0.9883213],"study_design_scores_gemma":[0.0001624572,0.00003022187,0.001440194,0.0001702123,0.00004155653,0.00004626397,0.000008043888,0.9684863,0.0006163983,0.02849155,0.00004900432,0.000457802],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.049832,0.0001987758,0.938436,0.001404807,0.00535182,0.001284411,0.0001305262,0.001240052,0.002121658],"genre_scores_gemma":[0.06314658,0.001228852,0.9212452,0.0009820749,0.002697664,0.001416461,0.0008424364,0.0001472033,0.008293582],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9878635,"threshold_uncertainty_score":0.9999084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1374330771222675,"score_gpt":0.3105569811471613,"score_spread":0.1731239040248937,"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."}}