Hi! I'm Binh. This website showcases my demo on Robust Speech Processing system

Accurately recognizing spoken language in challenging conditions using advanced algorithms, enabling efficient communication between humans and machines.


Speaker Diarization

Speaker diarization aims to answer the question of “who spoke when”. In short: diariziation algorithms break down an audio stream of multiple speakers into segments corresponding to the individual speakers.

waveImage from


Target Speaker Separation

By leveraging a reference signal from the target speaker, system can effectively separate the voice of a target speaker from complex multi-speaker signals.


Noise Cancelling

Selectively filter out unwanted sounds while preserving human speech, making it ideal for environments where clear communication is critical.