{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00556558,0.004361456,0.003019402,0.0009945967,0.001355543,0.003533031,0.004413714,0.005466733,0.02571841],"category_scores_gemma":[0.01605121,0.0008698766,0.001752318,0.0009927267,0.001120038,0.004424572,0.006598333,0.004921693,0.03919101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001544117,"about_ca_system_score_gemma":0.003105059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01503148,"about_ca_topic_score_gemma":0.01834915,"domain_scores_codex":[0.9944363,0.002415719,0.0003285542,0.00123932,0.001075706,0.0005043317],"domain_scores_gemma":[0.9929175,0.003352901,0.0001521146,0.001699458,0.001322671,0.000555329],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001495413,0.0008196731,0.000961764,0.002201421,0.0003578155,0.0004396302,0.0004738571,0.01392341,0.01253018,0.003996191,0.6758694,0.2869312],"study_design_scores_gemma":[0.00199246,0.001658339,0.006344737,0.0008247322,0.0003681662,0.001536685,0.00169813,0.3658085,0.04942103,0.02728229,0.5424863,0.0005786634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1161936,0.01821508,0.3075167,0.01548987,0.01174232,0.004121928,0.3190868,0.1419775,0.06565621],"genre_scores_gemma":[0.1117819,0.001929878,0.1512739,0.002607852,0.001106626,0.003507816,0.6804968,0.004981196,0.04231405],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02571841,"threshold_uncertainty_score":0.08603668,"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."}}