{"id":"W2141401351","doi":"10.1109/mmsp.2007.4412892","title":"Combining Vocal Source and MFCC Features for Enhanced Speaker Recognition Performance Using GMMs","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Mel-frequency cepstrum; Speech recognition; Crest factor; Computer science; Cepstrum; Vocal tract; Mixture model; Pattern recognition (psychology); Artificial intelligence; Speaker recognition; Centroid; Feature extraction; Bandwidth (computing)","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":[0.0004858463,0.0001167359,0.0001291014,0.000112472,0.0002027248,0.0001372945,0.0001530834,0.00007412345,0.00004971574],"category_scores_gemma":[0.00005879754,0.0001046152,0.00004634091,0.000163158,0.00003790663,0.000402449,0.00005938171,0.00008321483,0.0000274096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000240997,"about_ca_system_score_gemma":0.00001754833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001197597,"about_ca_topic_score_gemma":0.00001800314,"domain_scores_codex":[0.9990819,0.00001710977,0.0001837647,0.0002866026,0.0001473986,0.0002832501],"domain_scores_gemma":[0.9994126,0.0002059353,0.00006401562,0.0001468524,0.00007748335,0.00009309797],"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":[0.00002813449,0.00002723535,0.0001182817,0.00001739605,0.000009841231,0.000001378811,0.0003432834,0.000003575846,0.01014884,0.0002520149,0.0001131139,0.9889369],"study_design_scores_gemma":[0.001331472,0.0002136865,0.008628985,0.0001318471,0.0000237225,0.0001640898,0.0003934214,0.1106988,0.8730829,0.001673405,0.003091087,0.0005666716],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3925873,0.0000177688,0.5999544,0.00007991228,0.0001397899,0.000115617,6.915391e-7,0.00009694255,0.007007577],"genre_scores_gemma":[0.6923848,0.00001383324,0.3062475,0.0005754603,0.00008088117,0.000005532194,0.000003259244,0.000009408122,0.0006793042],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9883702,"threshold_uncertainty_score":0.4266084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03914357583190128,"score_gpt":0.2683018335022468,"score_spread":0.2291582576703455,"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."}}