{"id":"W3005705715","doi":"10.48550/arxiv.2002.05511","title":"Deep Autotuner: a Pitch Correcting Network for Singing Performances","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Singing; Intonation (linguistics); Computer science; Speech recognition; Spectrogram; Set (abstract data type); Convolutional neural network; Task (project management); Artificial neural network; Artificial intelligence; Improvisation; Acoustics; Engineering; Linguistics","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":[0.0003397402,0.0009640115,0.0005156939,0.000421947,0.000252287,0.0004305269,0.001520903,0.0006907834,0.002643425],"category_scores_gemma":[0.0007720782,0.000336671,0.0004511937,0.0003733743,0.0003168417,0.0006773246,0.0008127208,0.00126447,0.001245356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005201327,"about_ca_system_score_gemma":0.0005958712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006377189,"about_ca_topic_score_gemma":0.01240125,"domain_scores_codex":[0.9998093,0.00001674024,0.000007369905,0.00009134395,0.00003800193,0.00003722247],"domain_scores_gemma":[0.9998218,0.00005308321,0.00002207646,0.00003992928,0.00004532587,0.0000178663],"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":[0.0003989759,0.0002304827,0.003520798,0.0001562826,0.0001717218,0.0002517255,0.0001148538,0.1567136,0.06236469,0.001604171,0.009867979,0.7646047],"study_design_scores_gemma":[0.00001583,0.0001032352,0.001431012,0.00001899915,0.00003260456,0.00006715642,0.00002138345,0.9755412,0.01865678,0.00124698,0.002849129,0.00001563161],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2424331,0.002820883,0.7121005,0.0005041435,0.0005000345,0.000137666,0.002054197,0.03083841,0.008610953],"genre_scores_gemma":[0.7951384,0.0007262172,0.1824076,0.0003332228,0.00009705097,0.0001212823,0.003898123,0.0005823759,0.01669575],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006377189,"threshold_uncertainty_score":0.01268011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07910396086697677,"score_gpt":0.1923905618322597,"score_spread":0.113286600965283,"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."}}