Heng Lu

speech synthesis (3) neural vocoder (2) duration informed attention network (2) in-context learning (1) named entity recognition (1) multimodal learning (1) prompt engineering (1) speaker embedding (1) autoregressive model (1) deep neural network (1) classifier-free guidance (1) latent diffusion model (1) rectified flow (1) singing voice synthesis (1) dialogue understanding (1) efficient computing (1) speaker identification (1) text-to-audio generation (1) audio synthesis (1) text classification (1)