IEEE International Conference on Acoustics, Speech, and Signal Processing · 2025
Cited
0
Resume (English only)
Academic Achievements
Published papers such as 'ASVspoof 5: Design, collection and validation of resources for spoofing, deepfake, and adversarial attack detection using crowdsourced speech' in Computer Speech & Language; 'Generalized Score Comparison-Based Learning Objective for Deep Speaker Embedding' in IEEE Access; presented 'SNR-Aligned Consistent Diffusion for Adaptive Speech Enhancement' at Interspeech; and 'Evidential-TTS: High Fidelity Zero-Shot Text-to-Speech Using Evidential Deep Learning' at ICASSP.
Research Experience
Since 1998, has been directing the Human Interface Laboratory, focusing on research in speech and audio signal processing, including speech recognition, speech synthesis, speech enhancement, realistic acoustics, acoustic event detection, audio source separation, and audio source localization with applications from machine learning.
Background
Research interests include speech signal processing, AI & machine learning, audio signal processing, etc. The lab also covers research in the field of Large Language Models.