{"id":"W6921056807","doi":"10.60864/1s30-t715","title":"Less peaky and more accurate CTC forced alignment by label priors","year":2024,"lang":"en","type":"article","venue":"IEEE SIGPORT","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Offset (computer science); Security token; Pipeline (software); Hidden Markov model; Pattern recognition (psychology); Bayesian probability; Prior probability; Training set","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":[0.001515322,0.001460254,0.0009121165,0.0006521409,0.0008101781,0.001674336,0.001445422,0.001700254,0.007037659],"category_scores_gemma":[0.008362426,0.0007233515,0.0007403162,0.0008757072,0.000770029,0.002883719,0.001572693,0.003988533,0.005923247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009311594,"about_ca_system_score_gemma":0.002005265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00925243,"about_ca_topic_score_gemma":0.01968565,"domain_scores_codex":[0.9987273,0.0002799587,0.00004788044,0.0005598116,0.000251758,0.000133308],"domain_scores_gemma":[0.9961665,0.001735325,0.0002232563,0.001103236,0.0006376774,0.0001340882],"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":[0.0007772357,0.0003092457,0.006384291,0.0002291828,0.0001321635,0.0003056467,0.0003360536,0.2010897,0.05344854,0.008125641,0.03643201,0.6924303],"study_design_scores_gemma":[0.00005333667,0.00007999951,0.001427162,0.00003521666,0.00002834413,0.0001418176,0.00005769368,0.9613915,0.02244147,0.007839755,0.006467159,0.00003647837],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06685081,0.0007096278,0.8976541,0.0006648112,0.0004150336,0.0001024937,0.001143611,0.02781118,0.004648453],"genre_scores_gemma":[0.6197971,0.0002400538,0.3526949,0.000988069,0.000172868,0.000235389,0.007140159,0.005106902,0.01362449],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00925243,"threshold_uncertainty_score":0.02354336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03190628355525705,"score_gpt":0.281614336227028,"score_spread":0.2497080526717709,"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."}}