{"id":"W2507780144","doi":"10.1109/mcas.2016.2583681","title":"Recent Developments in Speech Enhancement in the Short-Time Fourier Transform Domain","year":2016,"lang":"en","type":"article","venue":"IEEE Circuits and Systems Magazine","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Sherbrooke; Concordia University","funders":"","keywords":"Short-time Fourier transform; Speech enhancement; Estimator; Computer science; Spectral density estimation; Wiener filter; Noise (video); Gaussian noise; Speech recognition; Fourier transform; Frequency domain; Algorithm; Spectral density; Noise reduction; Artificial intelligence; Mathematics; Fourier analysis; Statistics; Telecommunications; Computer vision","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":[0.001301716,0.0001730814,0.0002468913,0.0001467804,0.00007331562,0.0001823467,0.0004938773,0.00006424927,0.00001161888],"category_scores_gemma":[0.00001525798,0.00009713475,0.00002287271,0.0004311751,0.00003309103,0.0003781994,0.0000288142,0.00009541958,0.00008431458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001076278,"about_ca_system_score_gemma":0.00008333054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005914549,"about_ca_topic_score_gemma":0.00005565177,"domain_scores_codex":[0.9982222,0.00009897952,0.0004526394,0.0003948484,0.0004053723,0.0004259962],"domain_scores_gemma":[0.9994538,0.00007181089,0.00005968101,0.0002936441,0.00004853679,0.00007246113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003437846,0.00006133209,0.001382007,0.00003523412,0.000007367692,0.00009792448,0.00113204,0.000001537761,0.03917048,0.0001274337,0.0005395107,0.9574417],"study_design_scores_gemma":[0.0121972,0.0008205869,0.06312194,0.005876894,0.00003013913,0.001644642,0.0007389912,0.004145057,0.2109599,0.008974535,0.6880079,0.003482204],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7695323,0.002690308,0.19002,0.004851721,0.00123847,0.001416947,0.000006281151,0.00008841482,0.03015561],"genre_scores_gemma":[0.996568,0.0004132109,0.001417224,0.0002696872,0.00009342837,0.00007430298,0.000001084588,0.00001085876,0.001152168],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9539595,"threshold_uncertainty_score":0.396104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02387619114841635,"score_gpt":0.2448962645437055,"score_spread":0.2210200733952891,"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."}}