{"id":"W3110458199","doi":"10.48550/arxiv.2011.11588","title":"The Zero Resource Speech Benchmark 2021: Metrics and baselines for\\n unsupervised spoken language modeling","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmark (surveying); Computer science; Zero (linguistics); Spoken language; Speech recognition; Language model; Resource (disambiguation); Natural language processing; Artificial intelligence; Linguistics; Computer network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006136731,0.0003002698,0.0003283659,0.0002517836,0.0003815019,0.0003397413,0.001527994,0.0002254972,0.00002319184],"category_scores_gemma":[0.0004573881,0.0002740049,0.0002340868,0.0007839241,0.00007056836,0.0001924572,0.001391188,0.0004052648,0.00002295093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007386131,"about_ca_system_score_gemma":0.000113315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001053865,"about_ca_topic_score_gemma":0.0000344654,"domain_scores_codex":[0.9980845,0.0001747345,0.0002423031,0.001013013,0.000145133,0.0003402873],"domain_scores_gemma":[0.9977116,0.0008483494,0.0001488691,0.0008798475,0.0001950299,0.0002163103],"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":[0.0007145158,0.0004012883,0.002163121,0.0009511531,0.001346056,0.00236251,0.004696321,0.1216063,0.000700151,0.1797291,0.01660306,0.6687264],"study_design_scores_gemma":[0.0003566296,0.00002575333,0.00002163361,0.00005024271,0.00008025152,0.0000048499,0.0004553568,0.9750056,0.0002933476,0.02027628,0.00309051,0.000339506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09729272,0.000501825,0.8977247,0.001037981,0.0002843647,0.0004768543,0.00005054837,0.0001685718,0.002462375],"genre_scores_gemma":[0.9703841,0.001006401,0.02686833,0.0004224662,0.0001986934,0.000003457074,0.00004264033,0.00003016569,0.001043735],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8730914,"threshold_uncertainty_score":0.9999712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09401508568117196,"score_gpt":0.2031982157580533,"score_spread":0.1091831300768813,"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."}}