{"id":"W2036704249","doi":"10.1016/j.sigpro.2014.03.010","title":"Musical-noise-free blind speech extraction integrating microphone array and iterative spectral subtraction","year":2014,"lang":"en","type":"article","venue":"Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Core Research for Evolutional Science and Technology; Japan Society for the Promotion of Science","keywords":"Noise (video); Computer science; Speech recognition; Independent component analysis; Speech enhancement; Iterative method; Microphone; Noise measurement; Microphone array; Estimator; Acoustics; Algorithm; Mathematics; Artificial intelligence; Noise reduction; Physics; Telecommunications; Statistics","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":[0.0007507298,0.001129622,0.0009531289,0.0007798356,0.0003449029,0.0006710501,0.001153231,0.001212464,0.001367918],"category_scores_gemma":[0.001664477,0.0005436904,0.0009511205,0.0005059923,0.0006084133,0.001594166,0.0009015738,0.0006838034,0.001696414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002254123,"about_ca_system_score_gemma":0.0006474476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000435567,"about_ca_topic_score_gemma":0.0008963768,"domain_scores_codex":[0.999089,0.0001631105,0.00007648746,0.0001827574,0.0004459443,0.00004273765],"domain_scores_gemma":[0.9992707,0.0002397729,0.00007864966,0.0001160569,0.0002640381,0.00003066325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003464643,0.00009588085,0.000721891,0.0004228586,0.0001426905,0.0001459534,0.0001640301,0.02029445,0.475975,0.005495231,0.0006906101,0.4955049],"study_design_scores_gemma":[0.00006826473,0.0003600118,0.001791661,0.00003963006,0.0001697385,0.001331541,0.00005164665,0.4650348,0.5153429,0.003499797,0.01215933,0.000150731],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003001037,0.0001477639,0.9961547,0.00001743581,0.00002070963,0.00001834533,0.000008607957,0.0003133265,0.0003180929],"genre_scores_gemma":[0.05168921,0.0002386992,0.9463241,0.00006361928,0.00005046233,0.0000605055,0.00006864905,0.00007055928,0.001434088],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001367918,"threshold_uncertainty_score":0.004576147,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01398790553547897,"score_gpt":0.2574314407150714,"score_spread":0.2434435351795924,"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."}}