Chenpeng Du

text-to-speech synthesis (3) speech editing (2) vector quantization (2) data augmentation (1) named entity recognition (1) multimodal learning (1) speech recognition (1) automatic speech recognition (1) speaker embedding (1) multimodal reasoning (1) acoustic model (1) gaussian mixture model (1) diffusion model (1) supervised fine-tuning (1) chain-of-thought prompting (1) real-time interaction (1) knowledge boundary (1) speech synthesis (1) mixture density network (1) self-supervised learning (1)