{"id":"W4293053484","doi":"10.1109/civemsa53371.2022.9853712","title":"Towards a Vowel Formant Based Quality Metric for Text-to-Speech Systems: Measuring Monophthong Naturalness","year":2022,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Formant; Naturalness; Computer science; Metric (unit); Vowel; Speech recognition; Quality (philosophy); Set (abstract data type); Variation (astronomy); Mean opinion score; Sound quality; Psychoacoustics; Artificial intelligence; Perception","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002104898,0.0009411514,0.0006090788,0.002029244,0.000355147,0.001619566,0.0006263921,0.0007045232,0.002186226],"category_scores_gemma":[0.007537907,0.0002162239,0.0005629275,0.000829662,0.0005696046,0.001847284,0.00115606,0.0008161223,0.001379544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005675874,"about_ca_system_score_gemma":0.0005110311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002281307,"about_ca_topic_score_gemma":0.002888731,"domain_scores_codex":[0.9982517,0.0003146986,0.0002005549,0.0003725801,0.0007763896,0.000084062],"domain_scores_gemma":[0.9956766,0.001141727,0.0004479341,0.0004424521,0.002104538,0.0001867297],"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":[0.001419018,0.0002723927,0.03670081,0.001296772,0.0003407584,0.0002196673,0.0007542045,0.03248058,0.2867329,0.002457055,0.008967563,0.6283582],"study_design_scores_gemma":[0.0001504422,0.002410627,0.1587265,0.0002240228,0.0003105299,0.000957213,0.001448942,0.5692604,0.237681,0.0067611,0.02173698,0.0003322625],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2819243,0.00190409,0.6991925,0.0003300662,0.0004258911,0.0003690785,0.003737033,0.004709761,0.007407236],"genre_scores_gemma":[0.7300453,0.000451372,0.2586039,0.0001373474,0.0001739862,0.0002945809,0.006804243,0.0006799829,0.002809398],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002281307,"threshold_uncertainty_score":0.01113188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05318697439513604,"score_gpt":0.3007061767012467,"score_spread":0.2475192023061107,"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."}}