{"id":"W3015280134","doi":"10.1109/icassp40776.2020.9053831","title":"Improving Speech Recognition Using Consistent Predictions on Synthesized Speech","year":2020,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Speech recognition; Computer science; Audio mining; Voice activity detection; Acoustic model; Speech processing; Point (geometry); Speech synthesis; Speech coding; Natural language processing; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001694532,0.001225472,0.0007538871,0.0003636154,0.000245482,0.0008673072,0.0006727653,0.0006660346,0.003165148],"category_scores_gemma":[0.007402811,0.0005178884,0.0004706059,0.0002461239,0.0004472074,0.001201176,0.0008500994,0.0011155,0.003009616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003415589,"about_ca_system_score_gemma":0.0008062553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002767372,"about_ca_topic_score_gemma":0.006278209,"domain_scores_codex":[0.9983089,0.0005958346,0.00007735343,0.0005568441,0.0003504803,0.0001105835],"domain_scores_gemma":[0.995644,0.003000693,0.0001865697,0.0004615191,0.0006367191,0.00007047766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009371625,0.0002469815,0.004822471,0.0003259582,0.0001394123,0.0003815449,0.0004595552,0.112452,0.5335041,0.0008199635,0.00280179,0.343109],"study_design_scores_gemma":[0.00007383777,0.000681399,0.008029076,0.00004893811,0.0001156328,0.0002115075,0.0002849815,0.7045006,0.2807231,0.0009678724,0.004273531,0.00008956578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3690534,0.0008354258,0.6115882,0.0005778724,0.0003035258,0.0001260268,0.001017301,0.01183957,0.004658736],"genre_scores_gemma":[0.8421433,0.0003701617,0.1513442,0.0001821249,0.00008441243,0.00009658036,0.002041084,0.0005860228,0.003152069],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003165148,"threshold_uncertainty_score":0.01058853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0889213252948868,"score_gpt":0.2574665341658127,"score_spread":0.1685452088709259,"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."}}