I make machines that sing, speak, play, and hear.
I am a PhD researcher at the Institut Polytechnique de Paris under the supervision of Dr. Gaël Richard and Dr. You (Neil) Zhang 张优 in the intersection of audio and machine learning. I have over six years of R&D experience and a strong background in signal processing. My research focuses on controllable and interpretable generative models, particularly on physically-inspired singing voice style transformation. I also produce music and play jazz/bossa-nova guitar as hobbies.
Interests
Development of audio‑based machines that are transparent and human‑empowering in topics such as:
- Singing Voice & Speech
- Music Generation and Editing
- (Differentiable) Digital Signal Processing
- Deep/Machine Learning
Selected Works
- “PitchSTAR: Self-Supervised Pitch Style Transfer with Complementary Temporal and Time-Agnostic Style Representations”. (ICASSP 2027 Submission). Demo.
- “MusicFlux: Flexible Conditioning for Text-Guided Music Generation and Editing”. (ICASSP 2027 Submission). Demo.
- Interspeech’s 2025 Speech Emotion Recognition Challenge (5th/93 teams): “Improving Speech Emotion Recognition Through Cross Modal Attention Alignment and Balanced Stacking Model”.