{"id":"W3095018479","doi":"10.48550/arxiv.2010.14230","title":"A Comparison of Discrete Latent Variable Models for Speech Representation Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Latent variable; Speech recognition; Representation (politics); Variable (mathematics); Word (group theory); Word error rate; Latent variable model; Artificial intelligence; Encoding (memory); Pattern recognition (psychology); Mathematics","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":[0.0060303,0.001023022,0.000937165,0.001450029,0.0003050414,0.002086298,0.001809289,0.001475125,0.002251005],"category_scores_gemma":[0.01522126,0.000494369,0.001220165,0.001503783,0.0005567982,0.003627951,0.001623696,0.002705628,0.001196383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001565102,"about_ca_system_score_gemma":0.001120708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006752482,"about_ca_topic_score_gemma":0.00637717,"domain_scores_codex":[0.9970593,0.001561564,0.0001825589,0.0004674872,0.0005980136,0.000131068],"domain_scores_gemma":[0.9920778,0.005889337,0.0001953367,0.000902438,0.0007514101,0.0001836287],"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":[0.00157989,0.0003731512,0.005155808,0.0005766709,0.000620759,0.00006024554,0.0002688614,0.3691659,0.003225313,0.03341297,0.006540316,0.5790201],"study_design_scores_gemma":[0.00003419833,0.0001209718,0.0007571981,0.00004052489,0.00002762258,0.00002481872,0.00003703862,0.9870798,0.0007458937,0.009945606,0.001164403,0.00002180299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05883524,0.00887713,0.9230778,0.001867009,0.0003605929,0.0001059315,0.001172614,0.00261638,0.0030874],"genre_scores_gemma":[0.6603885,0.006978991,0.3206728,0.0005170534,0.0002704212,0.0003667668,0.005785828,0.0005222366,0.004497457],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006752482,"threshold_uncertainty_score":0.0318917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.227479796704191,"score_gpt":0.2623826478792052,"score_spread":0.03490285117501421,"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."}}