{"id":"W4391825020","doi":"10.1016/j.specom.2024.103044","title":"On intrusive speech quality measures and a global SNR based metric","year":2024,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"National Key Research and Development Program of China Stem Cell and Translational Research; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"PESQ; Computer science; Intelligibility (philosophy); Speech recognition; Metric (unit); Distortion (music); Speech enhancement; Speech processing; Signal-to-noise ratio (imaging); PSQM; Computation; Voice activity detection; Artificial intelligence; Algorithm; Noise reduction; Bandwidth (computing); Telecommunications; Engineering","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":[0.001174581,0.0001618423,0.0001719501,0.0001992716,0.0002226414,0.0006754919,0.001061292,0.00008638292,0.00001333931],"category_scores_gemma":[0.0004734157,0.0001473169,0.00005907312,0.001472409,0.00008177054,0.0005010549,0.000332071,0.0002650325,0.00008982955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001916649,"about_ca_system_score_gemma":0.000167089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001416646,"about_ca_topic_score_gemma":0.00008986961,"domain_scores_codex":[0.9983522,0.0002824054,0.0002667767,0.0004021724,0.0004715793,0.0002248071],"domain_scores_gemma":[0.9980279,0.0004400036,0.00008720202,0.001202169,0.0001487461,0.00009398694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001404343,0.0000662093,0.0003238127,0.00005896544,0.0000230951,0.00001298783,0.0001662126,0.00003357863,0.001058421,0.04330406,0.001126782,0.9538118],"study_design_scores_gemma":[0.001690404,0.0004722529,0.02057329,0.001163049,0.00008056503,0.0001792237,0.0002152697,0.05754531,0.3960955,0.48437,0.03611048,0.0015047],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1839968,0.02010015,0.7233428,0.02370649,0.0006643176,0.0006684769,0.00002626616,0.001642156,0.04585247],"genre_scores_gemma":[0.8551338,0.0001424559,0.1438983,0.0007133162,0.0000309895,0.00001117608,0.000009235687,0.000008239323,0.00005250272],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9523071,"threshold_uncertainty_score":0.6513784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03177723736601459,"score_gpt":0.3269485681240554,"score_spread":0.2951713307580408,"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."}}