{"id":"W4399527282","doi":"10.1109/taffc.2024.3412152","title":"Controllable Multi-Speaker Emotional Speech Synthesis With an Emotion Representation of High Generalization Capability","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Affective Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Generalization; Speech recognition; Emotion recognition; Representation (politics); Speaker recognition; Computer science; Emotion classification; Psychology; Artificial intelligence; Mathematics","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":[0.0005107594,0.0002190313,0.0003021118,0.0003768333,0.0002545738,0.0001893491,0.0002188328,0.00009773653,0.0001056407],"category_scores_gemma":[0.00004870035,0.0001967344,0.0001424949,0.0009886007,0.00008219524,0.0007654346,0.00000357416,0.0001918917,0.0000343946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001851404,"about_ca_system_score_gemma":0.00008397092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002683714,"about_ca_topic_score_gemma":0.0001223042,"domain_scores_codex":[0.9977871,0.0005216506,0.0003410944,0.0007011369,0.0004202938,0.0002287221],"domain_scores_gemma":[0.9981914,0.0008471977,0.0001172314,0.0003970928,0.0003544259,0.00009263898],"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":[0.0001125326,0.0008635604,0.0002375979,0.0001228505,0.0002529285,0.00002426976,0.001009105,0.09840456,0.01177478,0.001575596,0.00002623488,0.885596],"study_design_scores_gemma":[0.0004510899,0.0002100698,0.005437187,0.000209621,0.00005280772,0.00004658262,0.00009137305,0.7537588,0.2391758,0.00035777,0.000006073403,0.0002027747],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3002662,0.00001159525,0.6983427,0.0001204765,0.0004844794,0.0003198757,0.00001880265,0.0003076401,0.0001281411],"genre_scores_gemma":[0.8884513,0.000006428077,0.1113368,0.00004089041,0.00006289653,0.00002530721,0.000006025202,0.00002197225,0.00004828008],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8853932,"threshold_uncertainty_score":0.8022597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02894511557105801,"score_gpt":0.2795308599183586,"score_spread":0.2505857443473006,"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."}}