{"id":"W2259135914","doi":"10.1016/j.specom.2015.12.001","title":"Cry-based infant pathology classification using GMMs","year":2015,"lang":"en","type":"article","venue":"Speech Communication","topic":"Infant Health and Development","field":"Health Professions","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Bill and Melinda Gates Foundation","keywords":"Mixture model; Discriminative model; Mel-frequency cepstrum; Pattern recognition (psychology); Artificial intelligence; Computer science; Infant crying; Speech recognition; Naive Bayes classifier; Support vector machine; Feature vector; Hidden Markov model; Maximum a posteriori estimation; Feature extraction; Medicine; Mathematics; Maximum likelihood; Crying; Statistics","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":[0.002586858,0.0001355164,0.0002140076,0.0001676618,0.0007729523,0.00001054063,0.0003905928,0.0002802092,0.0000947165],"category_scores_gemma":[0.0003868898,0.0001295194,0.00003228222,0.0003021299,0.000080899,0.0001432301,0.0001612785,0.00063279,0.0006650614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006103876,"about_ca_system_score_gemma":0.00179619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006297028,"about_ca_topic_score_gemma":0.0002765057,"domain_scores_codex":[0.9971578,0.001212933,0.0006884783,0.0002135172,0.0002871007,0.0004401742],"domain_scores_gemma":[0.9972349,0.0002760001,0.000419067,0.001236063,0.000608425,0.0002254748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001545103,0.001025036,0.6543431,0.0009953649,0.00007881365,0.00004065132,0.05069892,0.000767968,0.02040202,0.09393778,0.077275,0.09889027],"study_design_scores_gemma":[0.005414462,0.0001952731,0.2079471,0.000586247,0.00005479245,0.00002589893,0.007381091,0.04937036,0.0018663,0.009064588,0.7172501,0.0008437616],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9147454,0.0006091946,0.01681705,0.008283746,0.0009452873,0.001665744,0.00001684077,0.0003319493,0.05658481],"genre_scores_gemma":[0.8886596,0.00007990644,0.1064281,0.003955293,0.0001102986,0.0001586478,0.0002893089,0.00002704017,0.0002917977],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6399751,"threshold_uncertainty_score":0.854824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2621689721373435,"score_gpt":0.4781006234133592,"score_spread":0.2159316512760158,"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."}}