{"id":"W109252123","doi":"10.21437/interspeech.2008-200","title":"Spectro-temporal features for robust far-field speaker identification","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Mel-frequency cepstrum; Speech recognition; Computer science; Filter bank; Speaker recognition; Reverberation; Filter (signal processing); Cepstrum; Pattern recognition (psychology); Identification (biology); Representation (politics); Artificial intelligence; Feature extraction; Acoustics; Computer vision","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":[0.0001154833,0.00008672477,0.00008814339,0.00005918662,0.0002082837,0.0001546701,0.0004259936,0.00004582408,0.00003023048],"category_scores_gemma":[0.00004956742,0.00007308974,0.00005962891,0.0001903703,0.00001826318,0.0004936309,0.00005237466,0.00006723183,0.00004568631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001726557,"about_ca_system_score_gemma":0.00005256515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002084008,"about_ca_topic_score_gemma":0.0000342171,"domain_scores_codex":[0.999193,0.000008470541,0.0001466325,0.0002850603,0.0001560843,0.0002108243],"domain_scores_gemma":[0.9994794,0.00004307689,0.00006403126,0.0002885929,0.00007133523,0.00005362752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006783621,0.0003013851,0.01174667,0.00009418539,0.00006413544,0.00007956286,0.001858115,0.0002516515,0.08418738,0.04227289,0.5946398,0.2644365],"study_design_scores_gemma":[0.0003907208,0.00008964875,0.01237043,0.000009885811,0.000004563831,0.0001230038,0.00003721449,0.003793271,0.9619179,0.004957909,0.01603961,0.000265844],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01107071,0.0001712224,0.9782123,0.003500482,0.0002802176,0.0001311345,5.299178e-7,0.0001993108,0.006434084],"genre_scores_gemma":[0.5447812,0.00001926972,0.4418768,0.001462491,0.0002331416,0.00001511687,0.000005650033,0.000008382561,0.01159796],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8777305,"threshold_uncertainty_score":0.2980513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02757675583121042,"score_gpt":0.2530429925056447,"score_spread":0.2254662366744343,"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."}}