Hello!
Welcome to my blog. I’m Dongchao Yang, a PhD student at CUHK working on speech and audio processing.
I plan to share my thoughts on:
- Audio Foundation Models — the architecture choices, training strategies, and what makes them work
- Generative Models for Audio — from diffusion models to language model approaches
- Research Tips — practical advice on experiments, writing, and the PhD journey
- Paper Reading Notes — breakdowns of interesting papers in our field
Why Blog?
Research papers are formal and structured. A blog gives me the space to share intuitions, failed experiments, and the messy middle of research that doesn’t make it into papers.
I hope these posts will be useful to others working in audio AI. Stay tuned!
# Here's a teaser — code snippets will be a regular feature
import torch
print("Let's build something cool together!")