{"id":"W4389191800","doi":"10.22215/etd/2023-15803","title":"Differentiation of Dry and Wet Cough Sounds using A Deep Learning Model and Data Augmentation","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"AGE-WELL","keywords":"Reverberation; Dry cough; Noise (video); Computer science; Speech recognition; Deep learning; Task (project management); Artificial intelligence; Test data; Training set; Machine learning; Pattern recognition (psychology); Image (mathematics); Engineering; Medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002115976,0.0001316881,0.0001888245,0.0002021082,0.0001144277,0.0001709436,0.0002446919,0.0001147072,0.00001696237],"category_scores_gemma":[0.0000773729,0.000130811,0.00002077111,0.000158464,0.00001500345,0.0004950328,0.0001292381,0.0001044465,0.000003045473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001683165,"about_ca_system_score_gemma":0.00004046782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001077439,"about_ca_topic_score_gemma":0.0004275732,"domain_scores_codex":[0.9989434,0.00004861955,0.0002444054,0.0004080204,0.0002512332,0.0001043044],"domain_scores_gemma":[0.9992846,0.0001102463,0.0002148794,0.0002688646,0.00008221887,0.00003918812],"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":[0.00004953036,0.00008474088,0.002654913,0.0007090499,0.0001952745,0.000004187605,0.008256828,0.0008363683,0.01218992,0.003301615,0.0001174846,0.9716001],"study_design_scores_gemma":[0.0001786646,0.00001290276,0.006993263,0.00007933017,0.00005191965,0.00000114811,0.0009969941,0.9887279,0.0008668582,0.001946251,0.000005105708,0.0001396287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5686806,0.0001022459,0.4297391,0.00002167655,0.0002037362,0.0001461136,0.0000128526,0.0001128163,0.0009807354],"genre_scores_gemma":[0.8124727,0.000873005,0.176759,0.00005052609,0.00005295475,0.00001617901,0.003230378,0.0000497718,0.006495459],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9878916,"threshold_uncertainty_score":0.5334316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08115625648407646,"score_gpt":0.32814461729633,"score_spread":0.2469883608122536,"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."}}