Awesome-Diffusion-Models-on-Speech

There are some papers about Diffusion models on Speech.

Basic diffusion models and Survey

• Denoising Diffusion Probabilistic Models in NeurIPS 2020, [paper], [code], [simpler code]
• Diffusion Models: A Comprehensive Survey of Methods and Applications in ACM Computing Surveys 2022, [paper], [code]
• Diffusion Models Beat GANs on Image Synthesis in NeurIPS 2021, [paper], [code]
• Awesome Diffusion Models, [code]
• Scalable Diffusion Models with Transformers (DiT), [code]

Conference paper

2024

2023

• Speech Enhancement and Dereverberation with Diffusion-based Generative Models in Arxiv 2023, [paper], [code]
• StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models in NeurIPS 2023, [paper], [code]
• Diffusion-based Generative Speech Source Separation in ICASSP 2023, [code]

2022

• DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism in AAAI 2022, [paper]
• Bilateral Denoising Diffusion Models in ICLR 2022, [paper]
• FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis in IJCAI 2022, [paper]
• Conditional Diffusion Probabilistic Model for Speech Enhancement in Arxiv 2022, [paper], [code]
• ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech in ACMMM 2022, [paper], [code]
• DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs in Arxiv 2022, [code]

2021 and before

• Diff-TTS: A Denoising Diffusion Model for Text-to-Speech in InterSpeech 2021, [paper]

• Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech in ICML 2021, [paper]

• Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search in NeurIPS 2020, [paper]