{"id":"W3186939564","doi":"10.18280/isi.260304","title":"Optimized Features Extraction from Spectral and Temporal Features for Identifying the Telugu Dialects by Using GMM and HMM","year":2021,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Telugu; Mel-frequency cepstrum; Hidden Markov model; Computer science; Artificial intelligence; Dimensionality reduction; Speech recognition; Feature extraction; Pattern recognition (psychology); Curse of dimensionality; Identification (biology); Feature (linguistics); 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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002863343,0.0001467003,0.0001745545,0.00009470303,0.0005105816,0.001411335,0.0001508882,0.0001002744,0.00001255829],"category_scores_gemma":[0.000309323,0.0001191493,0.00005797621,0.0002026964,0.00007380842,0.003015319,0.00007819872,0.0001208476,0.000002455965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007475432,"about_ca_system_score_gemma":0.00005852032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001735268,"about_ca_topic_score_gemma":0.00002977261,"domain_scores_codex":[0.9990519,0.00008434483,0.0002864401,0.0001830908,0.0001919635,0.0002022028],"domain_scores_gemma":[0.9991103,0.0002933577,0.000201715,0.0001841143,0.0001463678,0.00006410979],"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":[0.0001621168,0.00006629185,0.0009278521,0.0003304589,0.0002221688,0.00001627968,0.01875244,0.0001340152,0.03032633,0.003429554,0.00806443,0.9375681],"study_design_scores_gemma":[0.006457177,0.0002489595,0.07858431,0.001073134,0.0003449903,0.00244435,0.01453921,0.270053,0.5440608,0.06676644,0.01320414,0.002223504],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3695146,0.001795653,0.6260819,0.0004254491,0.0005835794,0.0004200502,0.00005380836,0.0001466337,0.000978329],"genre_scores_gemma":[0.8302765,0.0001452567,0.1688533,0.0003765604,0.000113772,0.00003814797,0.0001053964,0.000009556263,0.0000814931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9353446,"threshold_uncertainty_score":0.9996253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0278661034268363,"score_gpt":0.2684506857284297,"score_spread":0.2405845823015934,"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."}}