Login / Signup
NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers.
Kai Shen
Zeqian Ju
Xu Tan
Eric Liu
Yichong Leng
Lei He
Tao Qin
Sheng Zhao
Jiang Bian
Published in:
ICLR (2024)
Keyphrases
</>
diffusion models
diffusion model
information diffusion
speech recognition
acoustic features
speech signal
audio features
automatic speech recognition
information retrieval
image processing
optical flow
audio visual
music information retrieval