{"id":"W4221140961","doi":"10.1109/jstsp.2022.3200909","title":"Are Discrete Units Necessary for Spoken Language Modeling?","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales; Canadian Institute for Advanced Research","keywords":"Computer science; Spoken language; Natural language processing; Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005433679,0.0001109673,0.000232387,0.0003178404,0.0002277371,0.0001319048,0.0006381836,0.00004272262,0.0000280378],"category_scores_gemma":[0.0001308975,0.0001041094,0.00005736223,0.001070405,0.00001373571,0.0004823192,0.00005841618,0.0004339674,4.916855e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000109714,"about_ca_system_score_gemma":0.0003104575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004797796,"about_ca_topic_score_gemma":0.000007052868,"domain_scores_codex":[0.998648,0.0001112336,0.0004415649,0.0001669482,0.0003992718,0.0002329108],"domain_scores_gemma":[0.99876,0.00009737162,0.0004705211,0.00009339083,0.0005094904,0.00006919086],"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":[0.0003968725,0.0005004467,0.002251628,0.0003472173,0.0001158784,0.0009953964,0.009654868,0.05828054,0.02054542,0.0004901586,0.001784545,0.904637],"study_design_scores_gemma":[0.00102075,0.0002141529,0.0002398287,0.0002040842,0.00002311026,0.0003713652,0.001806499,0.9791167,0.01049437,0.005379192,0.0008444281,0.000285525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3395241,0.0007416249,0.6578439,0.001173572,0.0002770355,0.0001247173,0.00000688571,0.00004024116,0.0002679066],"genre_scores_gemma":[0.9736285,0.000008380566,0.02542883,0.0004907949,0.0003039247,0.00001021447,0.000001413606,0.00001285387,0.0001150581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9208362,"threshold_uncertainty_score":0.4245457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04163231579509832,"score_gpt":0.2834469320030519,"score_spread":0.2418146162079536,"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."}}