{"id":"W2109302000","doi":"10.1109/vecims.2005.1567572","title":"Accent adaptation in speech user interface","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Defense Advanced Research Projects Agency","keywords":"Speech recognition; Computer science; Stress (linguistics); Utterance; Word error rate; Hidden Markov model; TIMIT; Adaptation (eye); Artificial intelligence; Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001106913,0.00005271881,0.00005723987,0.00009504962,0.00001600863,0.00008488235,0.000226521,0.00002627004,0.0002923102],"category_scores_gemma":[0.00001386742,0.00004612885,0.00002194843,0.0002151028,0.000006700572,0.0002962182,0.00004781969,0.00004040765,0.0003962167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003264872,"about_ca_system_score_gemma":0.00001374799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004305158,"about_ca_topic_score_gemma":0.0007584176,"domain_scores_codex":[0.9994482,0.00002680927,0.0001312282,0.000159106,0.000120102,0.0001145257],"domain_scores_gemma":[0.9997408,0.00003980385,0.00002182787,0.0001494232,0.00002789659,0.00002027848],"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":[0.000006003595,0.0002145205,0.002550974,0.000003880137,0.000003814597,0.00003235208,0.0002030305,0.0002466548,0.001987897,0.06019497,0.007466712,0.9270892],"study_design_scores_gemma":[0.00116594,0.00006778988,0.09879469,0.00005362829,0.000004161322,0.00005147434,0.0002814665,0.4125439,0.4116428,0.0213093,0.05346413,0.0006207266],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09490965,0.00001574741,0.8123727,0.001025546,0.0001593091,0.00008720908,3.9682e-7,0.0001352542,0.09129413],"genre_scores_gemma":[0.8140114,0.00000333152,0.1817298,0.0002433558,0.00002298435,0.000004558074,9.549519e-7,0.000003137879,0.003980543],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9264685,"threshold_uncertainty_score":0.5092697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02355940262558318,"score_gpt":0.2494710618601507,"score_spread":0.2259116592345675,"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."}}