{"id":"W2075449699","doi":"10.1109/icassp.2014.6854638","title":"Phone sequence modeling with recurrent neural networks","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; TIMIT; Phone; Speech recognition; Artificial neural network; Word error rate; Decoding methods; Language model; Artificial intelligence; Recurrent neural network; Sequence (biology); Classifier (UML); Acoustic model; Context model; Complementarity (molecular biology); Hidden Markov model; Speech processing; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001683123,0.00008589935,0.00009091501,0.00003845776,0.00007005245,0.0001111984,0.0003365328,0.00002657688,0.00006058007],"category_scores_gemma":[0.00001764,0.00006031115,0.00002776315,0.0001842862,0.00001626315,0.0002464844,0.00005642039,0.00008469428,0.00005716699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001229138,"about_ca_system_score_gemma":0.00001028226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001934558,"about_ca_topic_score_gemma":0.00001735885,"domain_scores_codex":[0.9992574,0.00004522344,0.000107081,0.0002407442,0.0001580483,0.000191507],"domain_scores_gemma":[0.9995028,0.00005347565,0.00002675883,0.0002731137,0.0000590637,0.00008478283],"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":[0.000005634286,0.00002655123,0.00006361143,0.000002776186,0.000005981522,0.000005068699,0.00005977871,0.02671339,0.00007555094,0.01315229,0.00023258,0.9596568],"study_design_scores_gemma":[0.0001090617,0.00003503861,0.00001829678,0.00001092943,0.000001918665,0.00002370519,0.000007419173,0.9988128,0.0002454616,0.0004655611,0.0001585985,0.0001111955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01585224,0.00001339174,0.9740021,0.0005616425,0.0001804858,0.00004744954,1.31263e-7,0.0002053312,0.009137283],"genre_scores_gemma":[0.8770805,0.000006786147,0.1219742,0.0007726231,0.00006019981,0.000006641988,7.458675e-7,0.000004587514,0.00009370778],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9720994,"threshold_uncertainty_score":0.2459417,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04426966286379785,"score_gpt":0.2465918878762613,"score_spread":0.2023222250124635,"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."}}