{"id":"W2099621636","doi":"","title":"Vocal Tract Length Perturbation (VTLP) improves speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":335,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Speech recognition; Vocal tract; Normalization (sociology); Convolutional neural network; Spectrogram; Artificial neural network; Test set; Dynamic time warping; Word error rate; TIMIT; Image warping; Artificial intelligence; Pattern recognition (psychology); Hidden Markov model","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001909501,0.000135676,0.000125533,0.0001280839,0.00009962726,0.0003426846,0.0003296562,0.00009381343,0.002343166],"category_scores_gemma":[0.0001362711,0.000110594,0.00008771928,0.0002212595,0.00002552469,0.001584058,0.00005039569,0.0001131992,0.005139957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003626118,"about_ca_system_score_gemma":0.0000309995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001075793,"about_ca_topic_score_gemma":0.00000766501,"domain_scores_codex":[0.9988604,0.00006464784,0.0002308194,0.0003454972,0.0002559561,0.0002426992],"domain_scores_gemma":[0.9991799,0.0001661344,0.00006627383,0.0002916715,0.000177275,0.0001187712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000001083639,0.00008251918,0.00002620575,0.000003534365,0.000005752305,0.000002649804,0.0000695294,4.41736e-8,0.004399523,0.0007057286,0.003368589,0.9913349],"study_design_scores_gemma":[0.001686939,0.0005854088,0.04752761,0.00007872809,0.0000415867,0.0004484887,0.0007308237,0.2405309,0.52996,0.1583865,0.01826332,0.001759718],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3839311,0.00004819433,0.3286797,0.008211552,0.0009938665,0.0008194505,0.000004411078,0.001231343,0.2760804],"genre_scores_gemma":[0.7033343,0.00003884849,0.2863952,0.002403005,0.0002199818,0.00009333124,0.00001821867,0.00001749494,0.007479699],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9895751,"threshold_uncertainty_score":0.9985688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0241960568558066,"score_gpt":0.2242876426069468,"score_spread":0.2000915857511402,"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."}}