Daniel D. E. Wong — accepted AI-conference papers

2025

Advancing Active Speaker Detection for Egocentric Videos

Jaesung Huh, Juan Azcarreta Ortiz, Anurag Kumar, Ashutosh Pandey, Ali Aroudi, Daniel D. E. Wong +3

ICASSP 2025accepted

This paper presents an improved approach to multimodal active speaker detection in egocentric videos, specifically designed to be robust against the rapid movements and motion blur commonly found in such videos. We propose two key techniques to improve the model’s resilience: (i) spatially fixing th…

Cited by 0 Source ↗Scholar ↗

2023

Leveraging Heteroscedastic Uncertainty in Learning Complex Spectral Mapping for Single-Channel Speech Enhancement

Kuan-Lin Chen, Daniel D. E. Wong, Ke Tan, Buye Xu, Anurag Kumar, Vamsi Krishna Ithapu

ICASSP 2023accepted

Most speech enhancement (SE) models learn a point estimate and do not make use of uncertainty estimation in the learning process. In this paper, we show that modeling heteroscedastic uncertainty by minimizing a multivariate Gaussian negative log-likelihood (NLL) improves SE performance at no extra c…

Cited by 2 Source ↗Scholar ↗