{"id":"W3028186063","doi":"10.21437/interspeech.2020-2687","title":"GEV Beamforming Supported by DOA-Based Masks Generated on Pairs of Microphones","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Beamforming; Microphone array; Computer science; Microphone; Preprocessor; Distortion (music); Speech recognition; Acoustics; Noise (video); Direction of arrival; Speech enhancement; Artificial neural network; Noise-canceling microphone; SIGNAL (programming language); Source separation; Background noise; Artificial intelligence; Telecommunications; Amplifier; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001980976,0.0003838596,0.0005008602,0.0001764199,0.00009218196,0.0002305978,0.001361025,0.0002678346,0.0001044294],"category_scores_gemma":[0.00005552682,0.0003378394,0.0001791371,0.0004336955,0.00005733055,0.0001200406,0.0006624194,0.0004881517,0.00004251943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005794551,"about_ca_system_score_gemma":0.0005385453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001141823,"about_ca_topic_score_gemma":0.000005606528,"domain_scores_codex":[0.9976951,0.00005415697,0.0005440006,0.0008884801,0.0004347825,0.0003834364],"domain_scores_gemma":[0.9983057,0.00006025741,0.0005491429,0.0007415887,0.000167393,0.0001759574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003963129,0.0001837171,0.0003301246,0.0004869207,0.0001043365,0.00006275772,0.0003098674,0.003382656,0.9378061,0.00008193595,0.0250021,0.03220986],"study_design_scores_gemma":[0.0003425841,0.0000896824,0.00005238613,0.0001644491,0.00001565507,0.000002837597,0.00001468123,0.03574374,0.9613807,0.0005036216,0.001308198,0.0003814971],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1063294,0.0003012147,0.8858449,0.003694613,0.0007357165,0.0003286879,0.00004817369,0.0005511042,0.00216621],"genre_scores_gemma":[0.589491,0.0000237802,0.4064649,0.003121021,0.0001243556,0.00002514814,0.0002054362,0.0000429116,0.000501412],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4831616,"threshold_uncertainty_score":0.9999074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02509699788498877,"score_gpt":0.2495704727428091,"score_spread":0.2244734748578203,"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."}}