{"id":"W4404783121","doi":"10.18653/v1/2024.emnlp-main.30","title":"EmphAssess : a Prosodic Benchmark on Assessing Emphasis Transfer in Speech-to-Speech Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales; Canadian Institute for Advanced Research","keywords":"Emphasis (telecommunications); Computer science; Benchmark (surveying); Speech recognition; Natural language processing; Artificial intelligence; Telecommunications","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000852617,0.0003103207,0.0003481907,0.000698149,0.00009290776,0.001396768,0.0009336618,0.0001524542,0.00006543605],"category_scores_gemma":[0.0000423009,0.000258158,0.0001427887,0.001932566,0.00002759967,0.001601606,0.0001138783,0.0002660906,0.0003796883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001965252,"about_ca_system_score_gemma":0.0003549444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004058969,"about_ca_topic_score_gemma":0.0002657145,"domain_scores_codex":[0.9970292,0.0001320196,0.0004886507,0.001004498,0.0006895692,0.0006560808],"domain_scores_gemma":[0.9986911,0.0002477685,0.00001662483,0.000716628,0.00006514018,0.0002627815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004797486,0.0005950905,0.0006592192,0.0003207573,0.00006941761,0.002382973,0.004886582,0.001889018,0.0104502,0.2561521,0.007380608,0.7151661],"study_design_scores_gemma":[0.002766445,0.001193933,0.00325865,0.002791631,0.00004251082,0.0006448781,0.0006751398,0.790149,0.09769516,0.0808512,0.01692236,0.003009069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.20227,0.0002898698,0.7086759,0.001588288,0.001582445,0.0007808974,0.000006977283,0.000738545,0.084067],"genre_scores_gemma":[0.9780062,0.000009969878,0.02019203,0.0007080726,0.0001690674,0.00009115722,0.000005294172,0.00002799452,0.0007901472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.78826,"threshold_uncertainty_score":0.9999871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03559975349177633,"score_gpt":0.2959456531634647,"score_spread":0.2603458996716883,"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."}}