{"id":"W4390917297","doi":"10.3389/fnins.2023.1351848","title":"Speaker-turn aware diarization for speech-based cognitive assessments","year":2024,"lang":"en","type":"article","venue":"Frontiers in Neuroscience","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Shenzhen University; National Natural Science Foundation of China","keywords":"Speaker diarisation; Computer science; Speech recognition; Cluster analysis; Channel (broadcasting); Microphone; Feature (linguistics); Similarity (geometry); Artificial intelligence; Speaker recognition; Telecommunications","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003935655,0.0001525338,0.0001540799,0.0004292391,0.0001278694,0.0005343828,0.0006484705,0.0000595979,0.000008425166],"category_scores_gemma":[0.0003480583,0.0001472261,0.00008094248,0.00127685,0.0001188794,0.0008299282,0.00007324585,0.000138577,0.00001519795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000794159,"about_ca_system_score_gemma":0.0002074603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003832916,"about_ca_topic_score_gemma":0.000003527622,"domain_scores_codex":[0.9982292,0.00008231302,0.000220309,0.0007404537,0.0003755739,0.0003521689],"domain_scores_gemma":[0.9993392,0.000213315,0.00005093376,0.0002263738,0.00007420105,0.00009598493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003061893,0.0002133341,0.007373369,0.0001163648,0.000007019561,0.0002483768,0.0001993436,0.00009507409,0.003289544,0.002728899,0.01164246,0.9740556],"study_design_scores_gemma":[0.0003340594,0.0001062106,0.003888744,0.0001461146,0.000008159274,0.00001065229,0.00004786014,0.9725754,0.01087462,0.003108726,0.00866072,0.0002387852],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002251022,0.00007388599,0.990051,0.000669212,0.005324153,0.0004220435,0.00003732249,0.0002286633,0.0009427159],"genre_scores_gemma":[0.7692725,0.00003791155,0.2271631,0.002527277,0.00009679095,0.0001414478,0.00001496465,0.00002624282,0.0007197671],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9738168,"threshold_uncertainty_score":0.6003705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03173854922503484,"score_gpt":0.3128822342037598,"score_spread":0.281143684978725,"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."}}