{"id":"W4287776902","doi":"10.48550/arxiv.2005.09587","title":"GEV Beamforming Supported by DOA-based Masks Generated on Pairs of\\n Microphones","year":2020,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Beamforming; Microphone array; Computer science; Preprocessor; Microphone; Distortion (music); Speech recognition; Noise (video); Acoustics; Speech enhancement; Direction of arrival; Artificial neural network; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004249932,0.001037859,0.0005958379,0.0003477386,0.0002345642,0.0003595631,0.0005928566,0.0005895964,0.002166243],"category_scores_gemma":[0.002120101,0.0004355593,0.0004017256,0.0003094241,0.0003526809,0.0008077537,0.0009937127,0.0006244697,0.001433678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002176403,"about_ca_system_score_gemma":0.0004515122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001595004,"about_ca_topic_score_gemma":0.00402882,"domain_scores_codex":[0.9996051,0.00008742596,0.00001733725,0.0001128513,0.0001327527,0.00004455141],"domain_scores_gemma":[0.9996294,0.0001473901,0.00005015208,0.00006211659,0.00007967907,0.00003123692],"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":[0.001226692,0.0001288561,0.002259583,0.0001868996,0.0001155881,0.0002418293,0.0001952759,0.1640165,0.2774014,0.006556435,0.002644385,0.5450265],"study_design_scores_gemma":[0.00002793482,0.0001295401,0.002302293,0.00001852792,0.00002393022,0.0002238835,0.00004192729,0.9321444,0.05927148,0.003018191,0.002763304,0.00003463347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04193046,0.0001490915,0.9545205,0.00009223576,0.0000818979,0.00002930912,0.0001449903,0.001041669,0.002009862],"genre_scores_gemma":[0.4585502,0.0002259826,0.5356128,0.0001244388,0.00006986266,0.00009066752,0.0006290897,0.0001612757,0.004535712],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002166243,"threshold_uncertainty_score":0.007246792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0659297570656686,"score_gpt":0.1863694278395565,"score_spread":0.1204396707738879,"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."}}