3 papers
eess.AS2026
FSD50K-Solo: Automated Curation of Single-Source Sound Events
Ningyuan Yang, Sile Yin, Li-Chia Yang +4
High-quality training datasets are essential for the performance of neural networks. However, the audio domain still lacks a large-scale, strongly-labeled, and single-source sound…
eess.AS2025
Real-Time System for Audio-Visual Target Speech Enhancement
T. Aleksandra Ma, Sile Yin, Li-Chia Yang +1
We present a live demonstration for RAVEN, a real-time audio-visual speech enhancement system designed to run entirely on a CPU. In single-channel, audio-only settings, speech enha…
eess.AS2025
Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations
T. Aleksandra Ma, Sile Yin, Li-Chia Yang +1
Speech enhancement in audio-only settings remains challenging, particularly in the presence of interfering speakers. This paper presents a simple yet effective real-time audio-visu…