I'm a Doctoral Researcher in Audio Signal Processing at Aalto University currently working on generative models for audio restoration and enhancement.
My work focuses on developing novel algorithms for audio restoration using diffusion models and other deep generative approaches. I'm particularly interested in historical audio restoration, including tasks like denoising, bandwidth extension, and dereverberation. Recently, I've been working on unsupervised and zero-shot approaches that can generalize well to real-world scenarios without requiring paired training data.
My research has been published in venues like IEEE/ACM TASLP, ICASSP, and IEEE Signal Processing Letters. I'm passionate about combining signal processing theory with modern deep learning techniques to push the boundaries of what's possible in audio enhancement while maintaining interpretability and robustness.