{"id":"W3161411634","doi":"10.1109/icassp39728.2021.9413680","title":"A Comparison of Discrete Latent Variable Models for Speech Representation Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Latent variable; Speech recognition; Artificial intelligence; Representation (politics); Encoding (memory); Word error rate; Variable (mathematics); Latent variable model; Word (group theory); 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":[0.000173727,0.00005348879,0.000160043,0.00004254888,0.00005959029,0.00006775785,0.0001554972,0.00003352798,0.0001188326],"category_scores_gemma":[0.000124867,0.00005138838,0.0000667477,0.000243288,0.000009267276,0.0002785903,0.00007654684,0.00004939248,0.000009789179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001152609,"about_ca_system_score_gemma":0.00004177982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002988551,"about_ca_topic_score_gemma":0.000006146691,"domain_scores_codex":[0.9992178,0.00005674571,0.0002180081,0.0002251327,0.0001632326,0.0001190637],"domain_scores_gemma":[0.9992723,0.0002002418,0.00007816933,0.00020707,0.0002042832,0.00003795685],"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":[0.00003512959,0.0003688643,0.004889742,0.000100133,0.0001186555,0.00001120474,0.001660016,0.03017467,0.04034403,0.3909688,0.002587369,0.5287414],"study_design_scores_gemma":[0.0001690826,0.00002503253,0.0001153881,0.00001291654,0.000006688885,0.000004672092,0.0001551089,0.778223,0.2049203,0.01582496,0.000481528,0.00006133714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004847016,0.00002926072,0.974301,0.0003577638,0.00009313137,0.00009798577,0.000001467286,0.00006978039,0.02020264],"genre_scores_gemma":[0.39546,0.000006312659,0.6019814,0.0000570099,0.00001382863,0.00001256771,0.000009404983,0.000004057436,0.002455381],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7480483,"threshold_uncertainty_score":0.2095557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09678490460931576,"score_gpt":0.3466243956047883,"score_spread":0.2498394909954725,"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."}}