{"id":"W3032201847","doi":"","title":"SpiCE: A New Open-Access Corpus of Conversational Bilingual Speech in Cantonese and English.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Transcription (linguistics); Spice; Sentence; Annotation; Natural language processing; Speech corpus; Storyboard; Phonetic transcription; Speech recognition; Linguistics; Artificial intelligence; Speech synthesis; Multimedia; 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":[],"consensus_categories":[],"category_scores_codex":[0.0005656009,0.00008767751,0.00015152,0.0000826334,0.00003322471,0.0003380994,0.0005612857,0.00005208274,0.00004427601],"category_scores_gemma":[0.0004762005,0.00007642994,0.00001198173,0.000354949,0.00003566834,0.0008995893,0.0005676495,0.00009661028,4.320966e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002206699,"about_ca_system_score_gemma":0.0001478117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002243294,"about_ca_topic_score_gemma":0.0002644454,"domain_scores_codex":[0.9990151,0.00008361334,0.0001905453,0.0002857704,0.000319369,0.0001056014],"domain_scores_gemma":[0.9994665,0.00007437942,0.0001248018,0.0001358997,0.0001175084,0.00008088714],"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":[0.0001271857,0.00004943464,0.01436636,0.0002163837,0.00002141994,0.00004906645,0.1507818,0.00007364901,0.0115736,0.005431973,0.0003007732,0.8170084],"study_design_scores_gemma":[0.01003786,0.0009740227,0.05760196,0.0007606678,0.0001385892,0.0001053368,0.01046207,0.7991656,0.08504624,0.02962498,0.004557213,0.001525424],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9866933,0.007929374,0.003411944,0.00121326,0.00003917208,0.0003579216,0.000003556254,0.00006750745,0.0002839899],"genre_scores_gemma":[0.9626037,0.00004110326,0.03677288,0.000431999,0.00009797738,0.000005641415,0.000008711297,0.000005686111,0.00003231745],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.815483,"threshold_uncertainty_score":0.3391205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04815606913529093,"score_gpt":0.3652228133420278,"score_spread":0.3170667442067369,"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."}}