{"id":"W4205101752","doi":"10.18280/ts.380623","title":"Dialect Identification in Telugu Language Speech Utterance Using Modified Features with Deep Neural Network","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Telugu; Computer science; Mel-frequency cepstrum; Hidden Markov model; Artificial neural network; Artificial intelligence; Identification (biology); Speech recognition; Language identification; Utterance; Natural language processing; Feature (linguistics); Feature extraction; Natural language; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002241497,0.000434217,0.0003283613,0.000476841,0.0002058929,0.0003552874,0.0003200834,0.0003187034,0.001686793],"category_scores_gemma":[0.0005930385,0.0001415064,0.0003835813,0.0002602941,0.0001233494,0.0004417428,0.0003969512,0.0005394182,0.0005941647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003168127,"about_ca_system_score_gemma":0.0002802922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008336741,"about_ca_topic_score_gemma":0.01080067,"domain_scores_codex":[0.9998332,0.00002531023,0.00001157987,0.00005489951,0.00004241722,0.00003250911],"domain_scores_gemma":[0.9998616,0.0000349636,0.00001069484,0.000009662781,0.00007113873,0.00001187649],"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":[0.0009309935,0.0003390143,0.01192882,0.0002326589,0.0001495957,0.0006300709,0.0004216086,0.05006382,0.09609936,0.0007313155,0.006227099,0.8322456],"study_design_scores_gemma":[0.00001494442,0.0002220814,0.01707242,0.00002770816,0.00006735829,0.000230538,0.0002350186,0.9489084,0.03014259,0.0005720935,0.002472619,0.00003429377],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6771667,0.001846585,0.3093736,0.0004268393,0.000436725,0.0001392613,0.001233826,0.002487386,0.006889129],"genre_scores_gemma":[0.943738,0.0004316058,0.04770289,0.00007688099,0.00004307384,0.00006031719,0.001721077,0.00006097793,0.00616516],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008336741,"threshold_uncertainty_score":0.01657647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02062981121650824,"score_gpt":0.245858799548895,"score_spread":0.2252289883323867,"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."}}