{"id":"W4245212475","doi":"10.1121/2.0000173","title":"A comparison of speech enhancement methods to extract Lombard speech in an external noise field","year":2016,"lang":"en","type":"article","venue":"Proceedings of meetings on acoustics","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Medical Protective Association; University of Ottawa","funders":"","keywords":"Speech enhancement; Intelligibility (philosophy); Speech recognition; Headphones; Noise (video); Computer science; Loudspeaker; Background noise; Noise reduction; Acoustics; Noise measurement; Artificial intelligence; Telecommunications; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00113098,0.0008683379,0.0006011944,0.001086749,0.0001637561,0.0004869924,0.0004080556,0.0008404223,0.001112002],"category_scores_gemma":[0.002819885,0.000287252,0.0004774941,0.0002840978,0.0002910522,0.0007172802,0.0004818313,0.0003709301,0.0005148692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001248244,"about_ca_system_score_gemma":0.000247726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005036091,"about_ca_topic_score_gemma":0.000801257,"domain_scores_codex":[0.9994873,0.0001219395,0.00004362631,0.0001084385,0.000195882,0.0000427883],"domain_scores_gemma":[0.9984691,0.0009249055,0.00008681932,0.0001013608,0.0003442132,0.00007360493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004264026,0.000377025,0.002415771,0.001003864,0.0003153305,0.0002066839,0.0003760084,0.004903093,0.5448468,0.0003532388,0.0003731563,0.440565],"study_design_scores_gemma":[0.0004698648,0.00780604,0.06702835,0.000147588,0.001110165,0.002852575,0.000555367,0.1786444,0.7336679,0.0005013589,0.006964432,0.0002519941],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6955534,0.006885452,0.2911195,0.000153275,0.0002515666,0.0002541648,0.0001493747,0.001330412,0.004302895],"genre_scores_gemma":[0.7310004,0.004612288,0.2587127,0.0001633561,0.0001471345,0.0002304306,0.0004212937,0.0001948516,0.004517525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00113098,"threshold_uncertainty_score":0.005981266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03418633532552796,"score_gpt":0.3731102150905025,"score_spread":0.3389238797649745,"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."}}