{"id":"W3013018143","doi":"10.1186/s13636-019-0169-5","title":"Improving dysarthric speech recognition using empirical mode decomposition and convolutional neural network","year":2020,"lang":"en","type":"article","venue":"EURASIP Journal on Audio Speech and Music Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Speech recognition; Computer science; Convolutional neural network; Hidden Markov model; Artificial intelligence; Mixture model; Preprocessor; Pattern recognition (psychology); Mel-frequency cepstrum; Feature extraction","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004894818,0.0003702655,0.0003984394,0.0001788632,0.001203788,0.001337988,0.0003283895,0.0001365866,0.0000174598],"category_scores_gemma":[0.000158468,0.0003403355,0.00009134485,0.0006927435,0.0001191677,0.00212153,0.000207812,0.0008268373,0.00001023963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001011697,"about_ca_system_score_gemma":0.0002806119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000373791,"about_ca_topic_score_gemma":0.000002906653,"domain_scores_codex":[0.9973596,0.0001416661,0.0005761109,0.0006967366,0.0005358508,0.0006900272],"domain_scores_gemma":[0.9983927,0.00009400759,0.0005251634,0.0001364343,0.0002419505,0.0006097192],"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":[0.0001050996,0.00004500554,0.001940454,0.00009706567,0.00001999718,0.000297013,0.0004825286,0.0005486564,0.0185422,0.000008882416,0.0005486095,0.9773645],"study_design_scores_gemma":[0.003171034,0.0009456339,0.004743565,0.001059027,0.0001182473,0.01351485,0.000187214,0.9286805,0.03875152,0.006839495,0.0006467028,0.001342148],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7658609,0.002207321,0.227917,0.003114356,0.000371739,0.0001521369,0.000003128551,0.0001915812,0.0001818159],"genre_scores_gemma":[0.7593045,0.00008868448,0.2325741,0.006381158,0.001604038,0.000002326852,0.000005640144,0.00003215719,0.00000739001],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9760224,"threshold_uncertainty_score":0.9999049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05367039716690022,"score_gpt":0.322775362156534,"score_spread":0.2691049649896338,"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."}}