{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004348367,0.0003031551,0.0002392636,0.0002858645,0.0001472405,0.0004790207,0.000239818,0.0001220442,0.0002663992],"category_scores_gemma":[0.00002482923,0.0002718066,0.0001744792,0.0002980763,0.00003060689,0.0003369106,0.00006059489,0.00009737852,0.0001259186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001277597,"about_ca_system_score_gemma":0.0002065322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001851841,"about_ca_topic_score_gemma":0.00001494525,"domain_scores_codex":[0.9979013,0.00006959959,0.0003799591,0.0008171477,0.0004495256,0.0003824716],"domain_scores_gemma":[0.9989101,0.0003500785,0.00004731747,0.0003687521,0.00007686642,0.0002468525],"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":[0.00009825113,0.0004591576,0.00001639233,0.0007488788,0.0001339956,0.00004005569,0.003111096,0.001895255,0.005763617,0.005541972,0.01384489,0.9683464],"study_design_scores_gemma":[0.0009219236,0.0003693249,0.00007072882,0.0002085417,0.00008625106,0.000006730823,0.0002509136,0.9870394,0.009146797,0.001129892,0.0004252136,0.0003442214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01136795,0.0003752662,0.9769415,0.003365984,0.0006426335,0.001348694,0.0000793423,0.0004766175,0.005402066],"genre_scores_gemma":[0.6212672,0.0002103103,0.3613103,0.006759645,0.000126642,0.0003979369,0.0000544602,0.00006754918,0.009805896],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9851442,"threshold_uncertainty_score":0.9999734,"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."}}