{"id":"W2901429777","doi":"10.1007/s10772-018-09564-8","title":"Evaluating noise suppression methods for recovering the Lombard speech from vocal output in an external noise field","year":2018,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"QUIET; Computer science; Noise (video); Noise reduction; Headphones; Acoustics; Background noise; Microphone; Speech recognition; Intelligibility (philosophy); Speech perception; Speech enhancement; Perception; Sound pressure; Telecommunications; Physics; Artificial intelligence; Psychology","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":[0.001612092,0.001159115,0.0007875481,0.0008554331,0.0003792027,0.000712319,0.0005823231,0.001330181,0.001323639],"category_scores_gemma":[0.005033276,0.0002840339,0.0005681041,0.0003996081,0.0004572373,0.0007571197,0.0006367083,0.0004347757,0.0005329514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003304714,"about_ca_system_score_gemma":0.0006988985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003378587,"about_ca_topic_score_gemma":0.003957998,"domain_scores_codex":[0.9993532,0.0001604659,0.00005339304,0.0001117573,0.0002595583,0.00006163921],"domain_scores_gemma":[0.996466,0.002432714,0.0001595351,0.0001338053,0.0006928701,0.0001149481],"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":[0.007634364,0.0008999615,0.005151076,0.001053632,0.0004751413,0.0002311285,0.0002669009,0.1294153,0.3209914,0.0006567411,0.000519671,0.5327047],"study_design_scores_gemma":[0.0001508818,0.002134096,0.007528652,0.00003492746,0.0003245941,0.0002531247,0.0001893576,0.8421642,0.1462851,0.0002888671,0.0006006414,0.00004559254],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5897242,0.002914651,0.4037841,0.0001268975,0.0001227342,0.0001806309,0.000137596,0.0007481395,0.002260957],"genre_scores_gemma":[0.8053404,0.001276936,0.1891112,0.00007775638,0.00007233613,0.0001125643,0.0003997443,0.0001561884,0.003452906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003378587,"threshold_uncertainty_score":0.00852567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0534927076411623,"score_gpt":0.4276633464048619,"score_spread":0.3741706387636995,"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."}}