PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Driven Adaptive Prior

By Sang-gil Lee, Heeseung Kim, Chaehun Shin, Xu Tan, Chang Liu, Qi Meng, Tao Qin, Wei Chen, Sungroh Yoon, Tie-Yan Liu. 2021

32 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xu Tan
2. Tao Qin
3. Rongjie Huang
4. Dong Yu
5. Tie-Yan Liu
6. Dongchao Yang
7. Yoshua Bengio
8. Li Deng

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “Tacotron 1/2 [72, 73] Ph→MelS NAR / Hybrid/Self-Att/CNN MelNet [361] Ch→MelS AR / RNN DeepVoice [8] Ch/Ph→MelS AR / CNN DeepVoice 2 [84] Ch/Ph→MelS AR / CNN DeepVoice 3 [264] Ch/Ph→MelS AR Seq2Seq CNN ParaNet [262] Ph→MelS NAR Seq2Seq CNN DCTTS [326] Ch→MelS AR Seq2Seq CNN SpeedySpeech [355] Ph→MelS”
• InstructTTS: Modelling Expressive TTS in Discrete Latent Space With Natural Language Style Prompt (2023, background): “Diffusion generative models are first proposed in [36] and achieve strong results in image generation [37]–[40] and speech synthesis [41]–[44].”
• Infergrad: Improving Diffusion Models for Vocoder by Considering Inference in Training (2022, unknown): “Diffusion models have been extensively used for generation tasks [3, 17, 18, 19, 20, 21] since their capability of generating high-fidelity samples matches the state-of-the-art autoregressive and GANs based methods.”
• A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI (2023, unknown): “Specifically, PriorGrad [50] first computes the mean and variance based on the conditional data, and then maps the computed statistics as the mean and variance of Gaussian prior.”
• Riemannian Score-Based Generative Modeling (2022, methodology): “In the Euclidean setting this idea has been successfully applied for several image processing problems such as deblurring, denoising or inpainting (see for instance Kawar et al., 2021a; Kawar et al., 2021b; Lee et al., 2021; Sinha et al., 2021; Batzolis et al., 2021; Chung et al., 2021).”
• AudioLDM 2: Learning Holistic Audio Generation With Self-Supervised Pretraining (2023, methodology): “In the realm of speech or audio synthesis, these models have been explored for both mel-spectrogram generation [31], [47] and waveform generation [48], [49], [50].”