{"id":"W3187244867","doi":"10.21437/interspeech.2021-1755","title":"The Zero Resource Speech Challenge 2021: Spoken Language Modelling","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Encoder; Natural language processing; ABX test; Zero (linguistics); Coding (social sciences); Speech recognition; Pipeline (software); Artificial intelligence; Baseline (sea); Word (group theory); Language model; Linguistics; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008132044,0.0003041958,0.0003166043,0.0001011147,0.0002715054,0.001142287,0.002081821,0.000284354,0.000430188],"category_scores_gemma":[0.0000859976,0.0002208545,0.0002950625,0.0001897445,0.00004743383,0.0001349875,0.002173853,0.0007220411,0.0002653314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006269461,"about_ca_system_score_gemma":0.0001447085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001912656,"about_ca_topic_score_gemma":0.00009520086,"domain_scores_codex":[0.9975439,0.0002300198,0.0003737492,0.0008586113,0.0005741652,0.0004195725],"domain_scores_gemma":[0.9972565,0.000455869,0.0001492703,0.001863399,0.0001373452,0.0001376637],"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":[0.000005688415,0.0000865045,0.000003181254,0.00004632041,0.0001100453,0.0003729587,0.002569241,0.001243543,0.00004601091,0.008372829,0.004189761,0.9829539],"study_design_scores_gemma":[0.0002630106,0.00002702694,0.00001390937,0.0003218835,0.00004012519,0.00007532386,0.002736467,0.8934771,0.009528986,0.0128331,0.07966123,0.001021785],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004872953,0.00295743,0.7864925,0.005339069,0.000748843,0.0002885486,0.000005949382,0.0003117576,0.1989829],"genre_scores_gemma":[0.1896691,0.00671828,0.7522148,0.002057426,0.001294677,0.0001873314,0.00008807634,0.0001250259,0.04764529],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9819321,"threshold_uncertainty_score":0.9998946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03830097918852758,"score_gpt":0.2562580682949662,"score_spread":0.2179570891064386,"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."}}