I make machines that sing, speak, play, and hear.

I am a researcher in the intersection of audio and deep learning currently working as a Music Generation intern at Telecom Paris. I have five years of experience in the field and a background in signal processing. I am also a hobbyist music producer, composer, programmer and guitarist.

Interests

Developing audio‑based machines that are transparent and human‑empowering in topics such as:

• Differentiable Digital Signal Processing
• Singing Voice
• Sound Matching
• Music/Speech Generation & Recognition
• Neural Audio Effects
• Speech Emotion, Age and Gender Recognition

Selected Works

• Interspeech’s SER Challenge (2025): Improving Speech Emotion Recognition Through Cross Modal Attention Alignment and Balanced Stacking Model
• Master’s Thesis (2024): Cross-Speaker Style Transfer for TTS with Singing Voice Conversion Data Augmentation, Style Filtering, and F0 Matching
• Interspeech’s SynData4GenAI (2024): Exploring synthetic data for cross-speaker style transfer in style representation based TTS
• GENEA (2023): Gesture Generation with Diffusion Models Aided by Speech Activity Information