{"id":"W2917672101","doi":"","title":"Voice biometrics distinction between English and Arabic using Sound Cleaner Filtering and SpeechPro SIS II analysis","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Formant; Vowel; Speech recognition; Computer science; Speaker recognition; Spectrogram; Software; Articulation (sociology); Sound quality; Arabic; Biometrics; Linguistics; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0003913634,0.0001354904,0.0002240059,0.0009301991,0.0003782852,0.000372989,0.0001863006,0.00007398613,0.00009745521],"category_scores_gemma":[0.0002603891,0.0001202037,0.00006055905,0.002766505,0.0001094279,0.0005288111,0.0002957206,0.00006559132,0.00001137713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003383053,"about_ca_system_score_gemma":0.000009595517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009099806,"about_ca_topic_score_gemma":0.00005479578,"domain_scores_codex":[0.9988467,0.00004906854,0.0002183837,0.0004473593,0.0002213566,0.0002171682],"domain_scores_gemma":[0.9990954,0.0002207533,0.00008495745,0.0002687911,0.0001972113,0.000132823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00000987223,0.00008232988,0.142015,0.00003722881,0.000558626,0.000008915861,0.001601543,0.000005068618,0.00250852,0.0005246205,0.0001683302,0.8524799],"study_design_scores_gemma":[0.001388424,0.0006628222,0.5042892,0.00006785114,0.002021637,0.00007616416,0.001032791,0.4096547,0.05988181,0.005321799,0.0135257,0.00207712],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5995433,0.00001795026,0.3984497,0.00005244829,0.0001038597,0.00004535176,0.000004201836,0.00009924979,0.001683971],"genre_scores_gemma":[0.8924615,0.0000116635,0.1070364,0.00008095445,0.0002370643,0.000001368639,0.000003073394,0.00000675586,0.000161164],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8504028,"threshold_uncertainty_score":0.4901764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05138435495405243,"score_gpt":0.2786003491946247,"score_spread":0.2272159942405723,"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."}}