{"id":"W2084178137","doi":"10.1016/j.specom.2006.10.002","title":"Noise estimation using speech/non-speech frame decision and subband spectral tracking","year":2006,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"Ontario Centres of Excellence","keywords":"Speech recognition; Computer science; Noise (video); Speech enhancement; Microphone; Spectral density; Signal-to-noise ratio (imaging); Mean opinion score; Background noise; Noise measurement; Noise power; Power (physics); Noise reduction; Artificial intelligence; Telecommunications; Engineering; Physics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008460579,0.0002782499,0.0002857435,0.0002888037,0.0006333877,0.0009178516,0.001162329,0.0001788825,0.00001302555],"category_scores_gemma":[0.0001291172,0.0002886415,0.0000755756,0.0007563096,0.0001220126,0.001919567,0.0004289577,0.0003975792,0.00003422788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001988771,"about_ca_system_score_gemma":0.00009842038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004429924,"about_ca_topic_score_gemma":0.0001839632,"domain_scores_codex":[0.9978665,0.0001092095,0.000538916,0.0005205956,0.0005269948,0.0004377782],"domain_scores_gemma":[0.9977065,0.0002425719,0.0003276047,0.00139402,0.0002199672,0.0001093347],"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":[0.00002849943,0.00018333,0.006722182,0.00004716385,0.00001484662,0.00003021194,0.0004534889,0.001753026,0.07137515,0.001884514,0.0002628677,0.9172447],"study_design_scores_gemma":[0.001047961,0.00007439136,0.02712332,0.0004401292,0.00003417994,0.0004234381,0.00006411294,0.2806074,0.5885929,0.100216,0.0007132339,0.0006628961],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6091188,0.0009379066,0.3874026,0.0004584204,0.0001078902,0.0002171325,0.000001515212,0.0001864739,0.001569294],"genre_scores_gemma":[0.5253203,0.00008507202,0.4743923,0.00007277699,0.00006298595,0.000003608515,0.00001467771,0.00001643651,0.00003186541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9165818,"threshold_uncertainty_score":0.9999565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.016970777521193,"score_gpt":0.2775899563125778,"score_spread":0.2606191787913847,"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."}}