{"id":"W2117817230","doi":"10.1109/issse.2007.4294413","title":"A Processing Method for Pitch Smoothing Based on Autocorrelation and Cepstral F0 Detection Approaches","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Speech recognition; Pitch detection algorithm; Smoothing; Computer science; Discriminative model; Cepstrum; Autocorrelation; Intonation (linguistics); Mel-frequency cepstrum; Tone (literature); Artificial intelligence; Pattern recognition (psychology); Feature extraction; Speech processing; Mathematics; Computer vision","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":[0.0006415075,0.0008642306,0.0006869095,0.001700507,0.0006533023,0.0005600605,0.0009513964,0.0008354508,0.003989914],"category_scores_gemma":[0.001531061,0.0004156215,0.0007601061,0.001176442,0.0004026821,0.0008860594,0.0004715511,0.0008163821,0.002994912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003889962,"about_ca_system_score_gemma":0.0007517604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002909427,"about_ca_topic_score_gemma":0.00356709,"domain_scores_codex":[0.9993777,0.00006128083,0.00004480961,0.0001887806,0.0002931298,0.00003429076],"domain_scores_gemma":[0.999164,0.0001725265,0.00005127514,0.0001431925,0.000434649,0.00003442411],"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":[0.0002249733,0.00007630207,0.000508592,0.0001555489,0.00004910423,0.0001359989,0.00008450978,0.004927095,0.1931405,0.00410858,0.003298905,0.7932898],"study_design_scores_gemma":[0.0001023932,0.0005162598,0.006631573,0.00005358882,0.0002739884,0.001667684,0.00007887818,0.6338634,0.295608,0.003991249,0.0570186,0.0001944014],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003494679,0.0002399957,0.9939804,0.00003832566,0.0001074268,0.00005861436,0.0000598963,0.001425604,0.0005951214],"genre_scores_gemma":[0.03332135,0.000267097,0.9630858,0.00004973821,0.00009093778,0.00009184456,0.0001925441,0.0001421433,0.002758509],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003989914,"threshold_uncertainty_score":0.01334757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06618200486706205,"score_gpt":0.2972780613994062,"score_spread":0.2310960565323442,"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."}}