{"id":"W4408691358","doi":"10.5753/eniac.2024.245057","title":"Phonetic segmentation for Brazilian Portuguese based on a self-supervised model and forced-alignment","year":2024,"lang":"pt","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Segmentation; Portuguese; Brazilian Portuguese; Artificial intelligence; Natural language processing; Image segmentation; Speech recognition; Computer vision; Pattern recognition (psychology); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006196199,0.0006750871,0.0007203144,0.000726867,0.0005195817,0.001278492,0.0006607343,0.0007368722,0.00276057],"category_scores_gemma":[0.001613742,0.0004116736,0.0009862948,0.0006184726,0.0003292795,0.0007234649,0.0004783485,0.00066677,0.001229799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007600014,"about_ca_system_score_gemma":0.001520695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03091471,"about_ca_topic_score_gemma":0.0481708,"domain_scores_codex":[0.9996271,0.00007873205,0.00002292466,0.0001742076,0.0000527605,0.00004425457],"domain_scores_gemma":[0.9995412,0.0002054151,0.00003352404,0.0000672304,0.0001221271,0.00003060172],"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":[0.001360326,0.0001960059,0.007360612,0.0003253671,0.0001833651,0.0004461512,0.001010288,0.2373798,0.08353826,0.003078856,0.002910555,0.6622103],"study_design_scores_gemma":[0.00001316118,0.00005564596,0.002968089,0.00001475355,0.00002697489,0.00006302069,0.00006747097,0.987971,0.007102886,0.0007341765,0.000965928,0.00001691102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3228231,0.0006980879,0.6635369,0.0003243729,0.0001835867,0.0001228423,0.0007911047,0.005965538,0.005554478],"genre_scores_gemma":[0.8148858,0.0002183944,0.1778002,0.00006609903,0.00003200437,0.00009848313,0.00135665,0.0005019029,0.005040483],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03091471,"threshold_uncertainty_score":0.06146955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03012983819008365,"score_gpt":0.2769381947926632,"score_spread":0.2468083566025796,"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."}}