NVAlign: Direct-Gradient Optimization for Non-Verbal Control in Continuous Autoregressive Flow Matching Text-to-Speech
NVAlign uses reward gradients to improve non-verbal tag control in flow-matching text-to-speech.
1 stories, newest first · one card per story
NVAlign uses reward gradients to improve non-verbal tag control in flow-matching text-to-speech.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views