{"id":"W4402275989","doi":"10.1515/phon-2024-0015","title":"The Mason-Alberta Phonetic Segmenter: a forced alignment system based on deep neural networks and interpolation","year":2024,"lang":"en","type":"article","venue":"Phonetica","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; Nvidia","keywords":"Computer science; Interpolation (computer graphics); Speech recognition; Two-alternative forced choice; Artificial intelligence; Artificial neural network; Classifier (UML); Testbed; Task (project management); Similarity (geometry); Natural language processing; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001051339,0.001109326,0.0005898218,0.0007871715,0.0008475673,0.001200338,0.002064246,0.001153689,0.01587247],"category_scores_gemma":[0.002567505,0.0007917782,0.0006181467,0.0007586068,0.0005865512,0.001720662,0.001781933,0.001827776,0.006236271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001105135,"about_ca_system_score_gemma":0.002715031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03646047,"about_ca_topic_score_gemma":0.08570433,"domain_scores_codex":[0.9993505,0.0001043621,0.00003452444,0.0002800647,0.0001683502,0.00006216087],"domain_scores_gemma":[0.9993258,0.0002184073,0.00004059478,0.0001611654,0.000197678,0.00005640414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001047409,0.0001280478,0.002641823,0.0002532968,0.0001610473,0.0004207619,0.0006447608,0.03623971,0.1001962,0.007115284,0.0298941,0.8212575],"study_design_scores_gemma":[0.0001377712,0.0002976221,0.00345278,0.00007754517,0.0001209625,0.0004067494,0.0002514395,0.8387129,0.09512793,0.008650422,0.05259843,0.0001655498],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.03662939,0.0005553592,0.8665932,0.0003004004,0.0005026282,0.0002171013,0.002129884,0.08385815,0.009213806],"genre_scores_gemma":[0.1957851,0.0001840763,0.7768999,0.0003794967,0.00006341845,0.0002540658,0.004836292,0.003116843,0.01848073],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.03646047,"threshold_uncertainty_score":0.07249647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007528713155730898,"score_gpt":0.2100760710545101,"score_spread":0.2025473578987793,"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."}}