{"id":"W2134865850","doi":"10.1109/iscas.2009.5118030","title":"A spectral matching method for pitch estimation from noise-corrupted speech","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Discrete cosine transform; Speech recognition; Noise (video); Computer science; Pitch detection algorithm; Matching (statistics); Harmonic; Frame (networking); Frequency domain; Spectral density estimation; Speech enhancement; Spectral density; Speech processing; Noise reduction; Pattern recognition (psychology); Artificial intelligence; Mathematics; Acoustics; Computer vision; Fourier transform; Image (mathematics); Telecommunications; Statistics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002705385,0.0001310218,0.0001611934,0.00007680472,0.000139928,0.0003503948,0.0004858409,0.00005406963,0.00003448908],"category_scores_gemma":[0.00005354976,0.0001149241,0.00007031606,0.0002581701,0.000005839469,0.0006960503,0.00003845556,0.00008996482,0.00004036905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003725015,"about_ca_system_score_gemma":0.00005182104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008098227,"about_ca_topic_score_gemma":0.000009856599,"domain_scores_codex":[0.9989106,0.00002312492,0.0002039888,0.0003790804,0.0001934446,0.0002897308],"domain_scores_gemma":[0.9993594,0.0001394755,0.00008040014,0.0002863149,0.00005497303,0.00007939954],"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":[0.00001019282,0.00004132869,0.00003441826,0.000005326724,0.000007135998,0.000006142393,0.0004175022,0.0005598743,0.07545757,0.004049064,0.0006142359,0.9187972],"study_design_scores_gemma":[0.0003518497,0.00006335751,0.001532425,0.00002141673,0.000007155679,0.00001320872,0.00001950534,0.3574109,0.4089332,0.2313194,0.0001552607,0.0001722316],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0306104,0.00003878394,0.9626647,0.003091674,0.0001696282,0.0001687299,0.00000186191,0.0003768226,0.002877375],"genre_scores_gemma":[0.1105364,0.000001071186,0.8876362,0.001434293,0.0001234236,0.000004667413,0.000007366217,0.000005966059,0.000250596],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.918625,"threshold_uncertainty_score":0.4686469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01715889976179657,"score_gpt":0.3037245129576917,"score_spread":0.2865656131958951,"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."}}