{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002557533,0.0002764651,0.0004635636,0.0002394473,0.0002422484,0.0001486749,0.001521236,0.0003193133,0.00005276519],"category_scores_gemma":[0.00007760137,0.000316237,0.0002171522,0.0004799379,0.00005818334,0.0002661656,0.001572351,0.0002526124,0.00002198393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004342135,"about_ca_system_score_gemma":0.0006476184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002128955,"about_ca_topic_score_gemma":0.00237405,"domain_scores_codex":[0.9982666,0.00009191917,0.0002896197,0.0006602938,0.000331861,0.0003597098],"domain_scores_gemma":[0.9985679,0.0001360631,0.0003909062,0.000407305,0.0003445969,0.0001531923],"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":[0.0001783854,0.0001798561,0.001140202,0.005197991,0.0006232727,0.0005046192,0.03392108,0.0004378307,0.007667959,0.01170281,0.01838772,0.9200583],"study_design_scores_gemma":[0.00151407,0.0001544766,0.02134585,0.003088162,0.000263041,0.00008212214,0.001897793,0.868992,0.04081568,0.02280694,0.03723497,0.001804921],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4109667,0.0007187261,0.5644984,0.01165171,0.0005650992,0.001110582,0.0001448765,0.002682391,0.007661541],"genre_scores_gemma":[0.1210319,0.00005678849,0.875681,0.0007132739,0.0001428506,0.00001715611,0.00006894083,0.0000457195,0.002242389],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9182534,"threshold_uncertainty_score":0.999929,"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."}}