ResearchDatasetsVccmDatasetVccmDatasetFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsContradictory-style GenerationVccmDataset4.71MOS-SA168Emotion TransferVccmDataset (test)100Accuracy21Text-to-SpeechVccmDataset (test A)0.954Pitch6Style-controllable Speech SynthesisVccmDataset C (test)0.85Pitch6Text-to-SpeechVccmDataset set D (test)—Primary metric0