{"id":"W1608817341","doi":"10.1109/icosp.2004.1452648","title":"A post-filter perceptual convolutive blind source separation approach for speech signal","year":2005,"lang":"en","type":"article","venue":"","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Blind signal separation; Speech recognition; Computer science; Masking (illustration); Frequency domain; Filter (signal processing); SIGNAL (programming language); Source separation; Filter bank; Residual; Algorithm; Telecommunications; Channel (broadcasting); 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":[0.0005202903,0.0001909362,0.0001820286,0.0001718466,0.0001563103,0.0002716237,0.0006079254,0.0001433788,0.0001180839],"category_scores_gemma":[0.00002785088,0.0001718608,0.000121345,0.0002212899,0.00006266379,0.001018904,0.000139766,0.0001581088,0.0001087472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007147125,"about_ca_system_score_gemma":0.0001054611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002202031,"about_ca_topic_score_gemma":0.00001892354,"domain_scores_codex":[0.998468,0.00009856093,0.0003027933,0.000509939,0.0003095146,0.0003111437],"domain_scores_gemma":[0.9989665,0.0001090112,0.00009895334,0.0003973143,0.0003274303,0.0001007569],"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":[0.0005667015,0.001993302,0.0002481486,0.00006398575,0.0002099417,0.000003698657,0.07821732,0.008988224,0.06803796,0.3468409,0.1065995,0.3882303],"study_design_scores_gemma":[0.001171109,0.0004513357,0.0001776548,0.000004363787,0.00001199979,0.00003818333,0.000520574,0.9117395,0.05405857,0.0008846439,0.03049732,0.0004447273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01163401,0.00001710614,0.9710422,0.001804385,0.00003032925,0.0008041629,0.000006280898,0.0006329127,0.01402859],"genre_scores_gemma":[0.422835,0.000001114241,0.5670756,0.002793542,0.0001595664,0.00009782649,0.0000327764,0.00001314886,0.006991491],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9027513,"threshold_uncertainty_score":0.7008279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02961375676257186,"score_gpt":0.297109754202004,"score_spread":0.2674959974394322,"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."}}