{"id":"W3029693316","doi":"","title":"Speech Transcription Challenges for Resource Constrained Indigenous Language Cree","year":2020,"lang":"en","type":"article","venue":"Workshop Spoken Language Technologies for Under-resourced Languages","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Word error rate; Transcription (linguistics); Speech recognition; Natural language processing; Word (group theory); Language model; Documentation; Artificial intelligence; Spoken language; Error analysis; Linguistics","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"],"consensus_categories":[],"category_scores_codex":[0.0005351214,0.000606126,0.0007315861,0.0004516295,0.0004407515,0.0002928646,0.00223148,0.0006558088,0.0000667932],"category_scores_gemma":[0.0008934751,0.0005646618,0.0004864249,0.0007150826,0.0003102236,0.0003019763,0.0002857289,0.0004786988,0.00003871632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001089667,"about_ca_system_score_gemma":0.00006714156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002916443,"about_ca_topic_score_gemma":0.0001464413,"domain_scores_codex":[0.9965929,0.00008450293,0.0005901841,0.00121447,0.0004602126,0.001057707],"domain_scores_gemma":[0.9973195,0.0009271252,0.0002917039,0.001139357,0.0001157816,0.0002065222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.000316496,0.0001427305,0.000005800517,0.0002632746,0.0001963683,0.0001747692,0.03043515,0.00004346432,0.03728726,0.009048005,0.00146389,0.9206228],"study_design_scores_gemma":[0.008404784,0.001217435,0.00009839588,0.0003336394,0.0002768422,0.0002512544,0.6216754,0.008532946,0.2935797,0.003095418,0.05992686,0.002607276],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2016483,0.02804213,0.6749737,0.06465973,0.0002908505,0.006049866,0.0004943321,0.01697792,0.006863102],"genre_scores_gemma":[0.8000911,0.0002164683,0.1946094,0.002696653,0.0003040606,0.0007351703,0.0001931866,0.0001468167,0.001007108],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9180155,"threshold_uncertainty_score":0.9996805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04157063800353791,"score_gpt":0.2814875973299665,"score_spread":0.2399169593264286,"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."}}