{"id":"W4417072973","doi":"10.1016/j.csl.2025.101923","title":"Enhanced audio-visual speech enhancement with posterior sampling methods in recurrent variational autoencoders","year":2025,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Speech enhancement; Inference; Intelligibility (philosophy); Sampling (signal processing); Autoencoder; Pattern recognition (psychology); Noise reduction; Posterior probability","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008913854,0.0007595244,0.0005195044,0.0002692624,0.0001748725,0.0005035633,0.0007090099,0.0005926199,0.001379252],"category_scores_gemma":[0.002053775,0.000288299,0.0007402326,0.0001864916,0.0003953978,0.0007406404,0.0008550411,0.001000364,0.0005969313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002328533,"about_ca_system_score_gemma":0.0004802164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001800748,"about_ca_topic_score_gemma":0.003188292,"domain_scores_codex":[0.9996905,0.00008833695,0.00001614202,0.00006679083,0.000114692,0.00002360956],"domain_scores_gemma":[0.9994355,0.0003322766,0.00003907665,0.00005595886,0.0001140837,0.00002308303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003507142,0.0001219207,0.0008135233,0.0002393752,0.0001490451,0.0002291613,0.0002195382,0.5193341,0.1167312,0.01227669,0.001660669,0.347874],"study_design_scores_gemma":[0.000006519696,0.00003909412,0.0001369721,0.000008642064,0.00001299517,0.00005381875,0.000008520439,0.9856103,0.01170074,0.001602683,0.0008100332,0.000009636139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01174277,0.0002998085,0.9865409,0.00006448277,0.00003806846,0.00001570047,0.00002917179,0.000474796,0.0007943783],"genre_scores_gemma":[0.4597911,0.0006398692,0.533464,0.0001773887,0.00008607925,0.000088051,0.0002991555,0.0003137082,0.00514064],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001800748,"threshold_uncertainty_score":0.004714191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01555674382515423,"score_gpt":0.3504463130887455,"score_spread":0.3348895692635913,"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."}}