{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001394387,0.0002106816,0.0003366945,0.0002759772,0.00003738153,0.0002079717,0.0009986016,0.0002206788,0.0003975087],"category_scores_gemma":[0.000319536,0.0001450045,0.0001967744,0.0004254267,0.00007662297,0.000117088,0.001478836,0.0006567318,0.0002785032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007779659,"about_ca_system_score_gemma":0.0002125073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004273215,"about_ca_topic_score_gemma":0.0004654533,"domain_scores_codex":[0.9978586,0.000270035,0.0006422499,0.0005879083,0.0004237406,0.0002174332],"domain_scores_gemma":[0.9983094,0.0005280282,0.0001641298,0.000838462,0.0001126827,0.00004730973],"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":[0.000002020541,0.00008759662,0.0006373043,0.0002447052,0.00002665152,0.000006711236,0.0005296983,0.000002942865,0.0001836267,0.001621885,0.0001095445,0.9965473],"study_design_scores_gemma":[0.0001409601,0.00003462438,0.006472182,0.001002855,0.00004492178,0.00003391677,0.001033514,0.6158885,0.04169385,0.3330947,0.0001889282,0.0003710055],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9025693,0.000777909,0.0110937,0.001888395,0.001193441,0.001370818,0.00008059229,0.0008986922,0.08012714],"genre_scores_gemma":[0.9237208,0.0000361617,0.0759384,0.00007383349,0.00005477354,0.00008661072,0.00001229778,0.00001262444,0.00006446357],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9961763,"threshold_uncertainty_score":0.591311,"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."}}