本文前置知识: Flow Matching: Flow Matching for Generative Modeling. 或者: Rectified Flow: ReFlow: Flow Straight and Fast: Le

Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow 论文: Flow Straight and Fast: Learning

AlignSTS: Speech-to-Singing Conversion via Cross-Modal Alignment 论文: AlignSTS: Speech-to-Singing Conversion via Cross-Mo

本文前置知识: DDPM: DDPM: Denoising Diffusion Probabilistic Model. Denoising Diffusion Implicit Models 论文: Denoising Diffu

RoPE / RoFormer: Enhanced Transformer with Rotary Position Embedding本文是论文 RoFormer: Enhanced Transformer with Rotary Pos

Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation本文是论文Large-Sca

本文前置知识: HiFi - GAN: HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis. EVA-

Robust Speech Recognition via Large-Scale Weak Supervision本文是论文Robust Speech Recognition via Large-Scale Weak Supervisio

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis本文是论文HiFi-GAN: Generative Adve

本文前置知识: DDPM: Denoising Diffusion Probabilistic Model. DiffSinger: Singing Voice Synthesis via Shallow Diffusion Me

2025.03.17: 更新Reverse Process中的描述. DDPM: Denoising Diffusion Probabilistic ModelDDPM Overview DDPM: Denoising Diffusio