{"id":"W2168166926","doi":"10.64152/10125/44034","title":"Establishing a methodology for benchmarking speech synthesis for computer-assisted language learning (CALL)","year":2005,"lang":"en","type":"article","venue":"Language learning & technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Benchmarking; Computer science; Benchmark (surveying); Pronunciation; Context (archaeology); Speech synthesis; Task (project management); Set (abstract data type); Artificial intelligence; Natural language processing; Programming language; Linguistics; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002085152,0.0003960196,0.0007299384,0.00100818,0.0005693214,0.0003067663,0.001395943,0.0006048497,0.0001156974],"category_scores_gemma":[0.005848415,0.0004073486,0.0003039041,0.0009040621,0.0001259737,0.0004265884,0.0004420869,0.000895158,0.00005450474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001641739,"about_ca_system_score_gemma":0.00006864405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007937371,"about_ca_topic_score_gemma":0.0001529915,"domain_scores_codex":[0.9966183,0.0004921673,0.0005779762,0.00104755,0.0002581722,0.001005795],"domain_scores_gemma":[0.9935427,0.005069263,0.0004208422,0.0006457588,0.0001972047,0.000124255],"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":[0.00002862864,0.00007023926,0.0003429526,0.00006088804,0.00008461563,0.00006190848,0.002202761,0.000325959,0.01729563,0.001748606,0.000260887,0.9775169],"study_design_scores_gemma":[0.003181583,0.001520993,0.0007348533,0.0005023299,0.0002810172,0.00138853,0.00946021,0.5809578,0.2530317,0.001306478,0.1453169,0.002317624],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09458516,0.000522847,0.8979239,0.002884108,0.0003710681,0.0005990572,0.000007754283,0.002334873,0.000771214],"genre_scores_gemma":[0.2127024,0.00001663513,0.7851581,0.0004376202,0.0005436991,0.0003249229,0.00002733643,0.00006279149,0.0007264976],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9751993,"threshold_uncertainty_score":0.9998378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03088655784593764,"score_gpt":0.2995842815383971,"score_spread":0.2686977236924594,"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."}}