{"id":"W2901145677","doi":"10.48550/arxiv.1811.09678","title":"Speech recognition with quaternion neural networks","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Quaternion; Context (archaeology); Artificial neural network; Convolutional neural network; Speech recognition; Focus (optics); ENCODE; Representation (politics); Filter (signal processing); Filter bank; Artificial intelligence; Process (computing); TIMIT; Pattern recognition (psychology); Hidden Markov model; Mathematics; Computer vision","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007993924,0.0007329998,0.0004639501,0.0004783718,0.000195172,0.001040389,0.0007196067,0.0006539056,0.004014577],"category_scores_gemma":[0.002495108,0.000307002,0.0005216701,0.0008153092,0.0005089928,0.001858426,0.0007288376,0.0008736119,0.001971544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006889996,"about_ca_system_score_gemma":0.0004346102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004195656,"about_ca_topic_score_gemma":0.003818814,"domain_scores_codex":[0.9994745,0.0001392105,0.00004243368,0.0001445256,0.0001630397,0.00003642608],"domain_scores_gemma":[0.9995779,0.0001426841,0.00005118892,0.00009961176,0.0001135799,0.00001491179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000291509,0.00006901928,0.0008530183,0.0002118061,0.0001175727,0.0001363299,0.0001119587,0.4816246,0.02409886,0.02939034,0.006723873,0.4563711],"study_design_scores_gemma":[0.000008358408,0.0000297955,0.0001658628,0.00001138401,0.000006917004,0.00002248694,0.000008682919,0.9844694,0.003757066,0.008754372,0.002757369,0.000008275854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02235581,0.001722986,0.9692115,0.0004646313,0.0002768979,0.00005325797,0.0003536561,0.00242206,0.003139183],"genre_scores_gemma":[0.6256934,0.002248608,0.3622312,0.0003497173,0.0002773238,0.0001484437,0.00156314,0.0001766734,0.007311431],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004195656,"threshold_uncertainty_score":0.01343012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08138138747732042,"score_gpt":0.1814880062847343,"score_spread":0.1001066188074139,"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."}}