{"id":"W2251877103","doi":"10.22215/etd/2010-09603","title":"Co-channel speech separation using state-space reconstruction and sinusoidal modelling","year":2010,"lang":"en","type":"dissertation","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"Speech recognition; Channel (broadcasting); Computer science; Separation (statistics); Source separation; Blind signal separation; Speech processing; Independent component analysis; Microphone; Microphone array; Speaker recognition; Artificial intelligence; Telecommunications; Machine learning","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":[0.0004455648,0.0006392895,0.0004949687,0.0005665068,0.0002487774,0.000803658,0.000416036,0.0006460564,0.003064186],"category_scores_gemma":[0.001509046,0.000279726,0.0007554815,0.0005706101,0.0002433955,0.0009529495,0.0006672805,0.0007930951,0.002417699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001811467,"about_ca_system_score_gemma":0.0005857858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001752905,"about_ca_topic_score_gemma":0.003013829,"domain_scores_codex":[0.999649,0.00009433828,0.00002615665,0.00007357042,0.0001181355,0.00003887619],"domain_scores_gemma":[0.9994227,0.0002854724,0.00003679862,0.0001053328,0.0001301421,0.00001966047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005825859,0.0001866145,0.0008348054,0.0001909753,0.0001402294,0.000132053,0.0001251435,0.07751788,0.1065023,0.008834857,0.002278939,0.8026735],"study_design_scores_gemma":[0.0000306766,0.0001067558,0.0008949473,0.00002170137,0.00005229464,0.0001814969,0.00002775706,0.922264,0.07006553,0.002120159,0.004209094,0.00002560892],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0100665,0.0002351472,0.9875548,0.0000770152,0.00006472361,0.00002179679,0.00005293344,0.0007671162,0.001159852],"genre_scores_gemma":[0.371134,0.0007438137,0.6143057,0.00008483491,0.0001354464,0.00009257056,0.000774919,0.0002913466,0.01243723],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003064186,"threshold_uncertainty_score":0.01025075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02253034375226863,"score_gpt":0.2951266469306769,"score_spread":0.2725963031784083,"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."}}