{"id":"W3048281638","doi":"10.1109/newcas49341.2020.9159810","title":"Deep Neural Network based Complex Spectrogram Reconstruction for Speech Bandwidth Expansion","year":2020,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Spectrogram; Computer science; Narrowband; Non-negative matrix factorization; Bandwidth (computing); Wideband; Speech recognition; Artificial neural network; Artificial intelligence; Speech processing; Matrix decomposition; Pattern recognition (psychology); Algorithm; Electronic engineering; Telecommunications; Engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001201091,0.0001383953,0.0001712465,0.00003202329,0.0002105522,0.0002585591,0.0004000395,0.00004699651,0.00009068642],"category_scores_gemma":[0.00003448576,0.0001214555,0.00009789748,0.0004358011,0.00002984839,0.0003851126,0.00006589708,0.00009568469,0.00001940203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002056408,"about_ca_system_score_gemma":0.00004098337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004182476,"about_ca_topic_score_gemma":0.00001157853,"domain_scores_codex":[0.9988053,0.0000280851,0.0002061968,0.0004190237,0.0001662073,0.0003751176],"domain_scores_gemma":[0.9994047,0.00006928662,0.00008184847,0.0002095726,0.00007205187,0.0001625606],"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":[0.00003421393,0.0000194252,0.0009416854,0.00002606021,0.000006985241,0.000006436756,0.00005433004,0.003529469,0.006288305,0.0005067291,0.003439705,0.9851466],"study_design_scores_gemma":[0.0005880391,0.0002134648,0.0004310245,0.000009781901,0.000005655865,0.00002832655,0.00001994152,0.9486515,0.04541094,0.002095671,0.002361264,0.0001844157],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01011136,0.00006267602,0.9809528,0.006573088,0.0003466599,0.0002414375,5.318689e-7,0.0004622305,0.001249202],"genre_scores_gemma":[0.3290783,0.000001531726,0.6664188,0.003998951,0.0004614262,0.000008961395,0.000006998121,0.00000870913,0.00001629876],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9849622,"threshold_uncertainty_score":0.4952811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03690807482018218,"score_gpt":0.25531104428735,"score_spread":0.2184029694671678,"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."}}