{"id":"W3135815897","doi":"10.1109/iscslp49672.2021.9362084","title":"Age-Invariant Speaker Embedding for Diarization of Cognitive Assessments","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Speaker diarisation; Utterance; Computer science; Speech recognition; Embedding; Invariant (physics); Cognition; Adversarial system; Training set; Speaker recognition; Artificial intelligence; Psychology; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000162962,0.00006181224,0.0001156401,0.00005283453,0.00004571677,0.00008157534,0.0001242745,0.00003491637,0.0002441364],"category_scores_gemma":[0.0003385183,0.00005755751,0.00006333508,0.0002194311,0.00001318074,0.000238121,0.00006608989,0.00002721201,0.00001850386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000123165,"about_ca_system_score_gemma":0.00007379932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004088328,"about_ca_topic_score_gemma":0.000008809376,"domain_scores_codex":[0.9993155,0.00004806729,0.0001648135,0.0002103708,0.0001465395,0.0001147241],"domain_scores_gemma":[0.9990869,0.0004134832,0.0000629135,0.0001329545,0.0002635882,0.00004022088],"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":[0.00002620897,0.0007179904,0.001049626,0.00008399655,0.0002353557,0.0001409825,0.001008684,0.00001695204,0.02472159,0.246543,0.001529483,0.7239261],"study_design_scores_gemma":[0.001515739,0.0001142154,0.005975646,0.0002005113,0.00005716355,0.00003155782,0.0007835165,0.2394528,0.7352278,0.01505895,0.001218517,0.0003636184],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005068588,0.000007780453,0.9677229,0.0001723467,0.0001816407,0.0001209747,0.000008489488,0.00004615596,0.02667111],"genre_scores_gemma":[0.5929077,0.000008297352,0.4047882,0.0004685138,0.00003171707,0.00002180919,0.00002902188,0.000006131565,0.001738585],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7235625,"threshold_uncertainty_score":0.2673123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04708542641867467,"score_gpt":0.3360434326566122,"score_spread":0.2889580062379375,"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."}}