{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001584063,0.0005442011,0.00110533,0.0003651341,0.0004982629,0.002197149,0.001443513,0.001518216,0.005094769],"category_scores_gemma":[0.014308,0.0006089761,0.0006316478,0.0006425502,0.002658047,0.006223135,0.001423471,0.003430412,0.002344294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007021674,"about_ca_system_score_gemma":0.0009603839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002197279,"about_ca_topic_score_gemma":0.001251578,"domain_scores_codex":[0.9979391,0.0007911911,0.0001415617,0.0006149422,0.0003812158,0.0001320605],"domain_scores_gemma":[0.9933817,0.004311427,0.0004346064,0.001167212,0.0004602446,0.0002446924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009088136,0.0002108985,0.006364057,0.00127047,0.0002020481,0.0004454342,0.00176601,0.1265911,0.03697465,0.4682609,0.008306048,0.3486996],"study_design_scores_gemma":[0.00008538322,0.0002324456,0.002541375,0.0001789293,0.0000596469,0.0002866201,0.0005339073,0.4232837,0.01248146,0.5473362,0.01289446,0.0000857933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04661629,0.003456594,0.9364214,0.004282621,0.0005293175,0.00006309961,0.0006964083,0.0008649119,0.007069382],"genre_scores_gemma":[0.8468307,0.002021729,0.145199,0.0009147361,0.0003398398,0.0002345871,0.0008963965,0.0003260114,0.003237093],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005094769,"threshold_uncertainty_score":0.01704371,"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."}}