{"id":"W4402112262","doi":"10.21437/interspeech.2024-552","title":"Quantifying the Role of Textual Predictability in Automatic Speech Recognition","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; University of Toronto","keywords":"Predictability; Computer science; Leverage (statistics); Lexicon; Speech recognition; Language model; Syntax; Natural language processing; Acoustic model; Semantics (computer science); Context (archaeology); Artificial intelligence; Hidden Markov model; Speech processing","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.005545248,0.001380146,0.0007842534,0.001187899,0.0006374127,0.002184975,0.0007387548,0.001212432,0.001026087],"category_scores_gemma":[0.05500997,0.0007554877,0.0004748674,0.001105818,0.001403769,0.004301871,0.001903924,0.001640542,0.0007148586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006033562,"about_ca_system_score_gemma":0.0008238036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003272491,"about_ca_topic_score_gemma":0.005065345,"domain_scores_codex":[0.9957191,0.00156279,0.0004659443,0.0008000506,0.00119229,0.0002597583],"domain_scores_gemma":[0.9117718,0.07390558,0.005037868,0.005894897,0.002784681,0.0006051769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001982528,0.0003561802,0.1388037,0.0005784908,0.0003948753,0.0008361941,0.00115973,0.4575332,0.1357944,0.006903084,0.00179101,0.2538668],"study_design_scores_gemma":[0.00002055897,0.0003998968,0.04263051,0.00005022325,0.0001014243,0.0003591765,0.0002049825,0.884467,0.06169819,0.009311657,0.0006505629,0.0001058714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6038793,0.0009979912,0.3878319,0.0009767722,0.000139954,0.0000549553,0.000658137,0.002218209,0.003242864],"genre_scores_gemma":[0.9816173,0.0001659626,0.01705591,0.00006783265,0.00007715176,0.00002067785,0.0003770433,0.0002609231,0.0003572803],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005545248,"threshold_uncertainty_score":0.02932638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05695116929226401,"score_gpt":0.289777918287595,"score_spread":0.232826748995331,"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."}}