{"id":"W2396030159","doi":"10.21437/interspeech.2013-432","title":"Using an autoencoder with deformable templates to discover features for automated speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; TIMIT; Spectrogram; Autoencoder; Hidden Markov model; Speech recognition; Artificial neural network; Artificial intelligence; Pattern recognition (psychology); Set (abstract data type); Dropout (neural networks); Task (project management); Test set; Machine learning","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":[0.000105722,0.0001399858,0.0001238292,0.000103381,0.0002178431,0.0007675073,0.0003058881,0.00004887184,0.00003940054],"category_scores_gemma":[0.00001434686,0.00009327372,0.00002491053,0.0003286666,0.00001551695,0.003331809,0.00006353723,0.00005332138,0.00006510101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003794444,"about_ca_system_score_gemma":0.00008234457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003114167,"about_ca_topic_score_gemma":0.00009121395,"domain_scores_codex":[0.9990054,0.00001228146,0.0001350737,0.0003258135,0.0001641091,0.0003573408],"domain_scores_gemma":[0.9993657,0.00002478084,0.00005551932,0.0002346087,0.0001828235,0.0001365262],"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":[0.000115409,0.0004997861,0.002856351,0.0002288565,0.000124389,0.00002574665,0.0025241,0.02104997,0.1762324,0.0004483222,0.03647218,0.7594225],"study_design_scores_gemma":[0.0003832315,0.0002448545,0.00147363,0.00007519447,0.000008373656,0.0001049158,0.0001053519,0.5536356,0.4403363,0.00310272,0.0002110497,0.0003187596],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3637427,0.000009846645,0.6334969,0.000491338,0.00007709169,0.0003992167,0.000002549257,0.0007087118,0.001071594],"genre_scores_gemma":[0.1371125,4.437372e-7,0.8614332,0.0008909247,0.00004594887,0.00003707983,0.000009711258,0.00001320775,0.0004569808],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7591037,"threshold_uncertainty_score":0.740109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04314113276841627,"score_gpt":0.2933091318944558,"score_spread":0.2501679991260396,"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."}}