{"id":"W4287591426","doi":"10.48550/arxiv.2011.11588","title":"The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Natural language processing; Benchmark (surveying); Artificial intelligence; Cluster analysis; Spoken language; Language model; Syntax; Speech recognition; Concatenation (mathematics); Pipeline (software); Representation (politics)","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":[0.007830624,0.004331748,0.001719558,0.003803545,0.001471672,0.002794548,0.003604047,0.003803816,0.006544],"category_scores_gemma":[0.0326134,0.0006266396,0.001184935,0.0024106,0.001492264,0.003471326,0.00455262,0.002836758,0.006665818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001872437,"about_ca_system_score_gemma":0.002218487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01221498,"about_ca_topic_score_gemma":0.01447313,"domain_scores_codex":[0.988299,0.005152146,0.001068716,0.001902571,0.002863429,0.0007140823],"domain_scores_gemma":[0.9872183,0.004984155,0.0006440805,0.003375585,0.003183829,0.0005939764],"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":[0.004226943,0.002840514,0.01025646,0.003576757,0.0009877479,0.0007222616,0.0008239268,0.1370883,0.03846437,0.01384465,0.2197732,0.5673949],"study_design_scores_gemma":[0.0007716849,0.003937421,0.02077994,0.0006461586,0.0003565984,0.001642585,0.001151901,0.7161611,0.1250989,0.03444114,0.09443035,0.000582194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2874869,0.01062728,0.4918418,0.001916194,0.00267969,0.003150905,0.08132084,0.0770546,0.04392176],"genre_scores_gemma":[0.3988619,0.001192971,0.336163,0.00085752,0.0003441473,0.004548833,0.2341766,0.00796861,0.01588636],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01221498,"threshold_uncertainty_score":0.04141277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0971620928814873,"score_gpt":0.2049767873225302,"score_spread":0.1078146944410429,"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."}}