{"id":"W4393770136","doi":"10.5281/zenodo.7356907","title":"LJ Speech - Aligned IPA transcriptions","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Speech recognition; Computer science; Natural language processing; Linguistics; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008984036,0.0002988989,0.0003022593,0.000750556,0.002229692,0.00221489,0.004080475,0.0002258211,0.01237241],"category_scores_gemma":[0.0007390332,0.0003247648,0.0001707379,0.001407161,0.0001375479,0.0004186002,0.001519361,0.0003963207,0.1848546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001602374,"about_ca_system_score_gemma":0.00001188486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008601343,"about_ca_topic_score_gemma":0.000003877317,"domain_scores_codex":[0.9968689,0.0005213706,0.0004197253,0.0008528084,0.0007713299,0.0005658653],"domain_scores_gemma":[0.9975469,0.00006924153,0.0001652028,0.001360393,0.0005533311,0.0003049058],"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":[0.000007023114,0.0001031129,1.095015e-8,0.00005923205,0.00005088589,0.00008460433,0.00008885405,9.856858e-7,0.000158545,0.0005149704,0.9217545,0.07717728],"study_design_scores_gemma":[0.0002738873,0.0001119102,0.00001767948,0.00006250406,0.00003018313,0.0002058428,0.00005201938,0.0001934806,0.0001737379,0.0003097475,0.9982153,0.0003537254],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00001277019,0.00004237685,0.01117554,0.001606814,0.0006795821,0.0005469966,0.9665603,0.002628105,0.01674752],"genre_scores_gemma":[0.00003360393,0.0004357164,0.001805677,0.0004116387,0.0002784645,1.62282e-7,0.9938699,0.00110985,0.002055],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1724822,"threshold_uncertainty_score":0.9999204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06039329554808336,"score_gpt":0.2634451578515846,"score_spread":0.2030518623035012,"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."}}