{"id":"W3028638700","doi":"","title":"Developing Resources for Automated Speech Processing of Quebec French","year":2020,"lang":"en","type":"preprint","venue":"SERVAL (Université de Lausanne)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Syllabification; Phonotactics; Computer science; Lexicon; Speech segmentation; Pronunciation; Phonetic transcription; Segmentation; Speech recognition; Natural language processing; Artificial intelligence; Speech processing; Phonology; Process (computing); Software; Linguistics; Syllable","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001554987,0.00227633,0.000941172,0.004854458,0.002124442,0.002237647,0.001784386,0.001049922,0.04058482],"category_scores_gemma":[0.005658991,0.0005965098,0.0008690871,0.002796148,0.000766708,0.002033849,0.001627605,0.0009092136,0.01583125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005966236,"about_ca_system_score_gemma":0.009325682,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.6681621,"about_ca_topic_score_gemma":0.6216085,"domain_scores_codex":[0.9987758,0.0003513512,0.00006259889,0.0003082251,0.0002631373,0.0002389045],"domain_scores_gemma":[0.9958788,0.001315913,0.000143042,0.0004570538,0.00200578,0.0001994269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001746133,0.000213084,0.00575552,0.001180225,0.0001964255,0.001368144,0.001940058,0.03162982,0.1049935,0.007287614,0.121477,0.7222126],"study_design_scores_gemma":[0.0003635528,0.0004302991,0.02631902,0.0005575334,0.0005709967,0.0006404051,0.003535322,0.3452103,0.1940445,0.005270243,0.4227694,0.0002884534],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1959841,0.003026921,0.5426871,0.001952924,0.000371897,0.003150319,0.09155842,0.08982973,0.07143868],"genre_scores_gemma":[0.3797472,0.00155073,0.3903904,0.000391028,0.0002187473,0.002090322,0.1655486,0.006966905,0.05309606],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3318379,"threshold_uncertainty_score":0.6675843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03823676035702916,"score_gpt":0.2513552363621726,"score_spread":0.2131184760051434,"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."}}