{"id":"W2989571531","doi":"10.1109/sped.2019.8906599","title":"FoR: A Dataset for Synthetic Speech Detection","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":169,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence; Natural language processing","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":[0.001167251,0.004192942,0.001607587,0.002997367,0.001128402,0.001332852,0.002877084,0.002996895,0.01633849],"category_scores_gemma":[0.003806616,0.0004479745,0.001515714,0.002184469,0.0005430497,0.001009581,0.001789241,0.002019739,0.026404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001189809,"about_ca_system_score_gemma":0.001484734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01315169,"about_ca_topic_score_gemma":0.02850116,"domain_scores_codex":[0.9981187,0.0004025042,0.0002660517,0.0004659971,0.0005553759,0.0001912731],"domain_scores_gemma":[0.9977046,0.0006202626,0.0001759503,0.0005195807,0.0007364329,0.0002432719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001327638,0.0009408128,0.005155356,0.002096428,0.0003083843,0.0008773571,0.0002415272,0.005727177,0.009279026,0.0009837461,0.8775744,0.09548806],"study_design_scores_gemma":[0.0009866751,0.0009401666,0.02923094,0.0005241001,0.0002824902,0.003306888,0.0009461319,0.04402836,0.02023329,0.002658878,0.8964717,0.0003905652],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0237493,0.001736927,0.006554581,0.0005123426,0.0008133026,0.0006060297,0.9511297,0.00899014,0.005907728],"genre_scores_gemma":[0.01207643,0.0002073721,0.007330823,0.0001414158,0.00007581643,0.0005404853,0.976612,0.000207731,0.002807929],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01633849,"threshold_uncertainty_score":0.0546577,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02481780576436919,"score_gpt":0.2639481081266526,"score_spread":0.2391303023622834,"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."}}