{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002070916,0.0001982072,0.0004493201,0.0001698309,0.0001088314,0.00008391631,0.0008870127,0.0001848891,0.00003227718],"category_scores_gemma":[0.0001078741,0.0002325124,0.0002404949,0.0004433245,0.0000429198,0.0003310361,0.0008062701,0.0003459553,0.0000183893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007757515,"about_ca_system_score_gemma":0.000112375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001201676,"about_ca_topic_score_gemma":0.000006509227,"domain_scores_codex":[0.9984148,0.0001429307,0.0002855822,0.0008286576,0.0001137942,0.0002142194],"domain_scores_gemma":[0.9984774,0.0002364256,0.0004074778,0.0005263173,0.0002331974,0.0001191881],"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":[0.00009459923,0.0001152713,0.002473454,0.0002063289,0.00017157,0.00003194445,0.0006794715,0.8169259,0.0004688906,0.1732873,0.0003664908,0.005178799],"study_design_scores_gemma":[0.0003112493,0.0000585007,0.00009089055,0.00007319404,0.00007191963,0.000001060696,0.0001317052,0.883013,0.003377043,0.1125116,0.0001467268,0.0002131512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02349253,0.00001946326,0.971479,0.0001501627,0.0002274287,0.0004058476,0.00001957933,0.0001747958,0.004031168],"genre_scores_gemma":[0.9242217,0.00003928778,0.07490078,0.00003159788,0.00003643033,0.000002629586,0.00004179466,0.00001421549,0.0007115681],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9007292,"threshold_uncertainty_score":0.9481579,"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."}}