Open access
2026
PTT-GGF Network: Robust Voice Activity Detection via Multimodal Gated Fusion in Complex Cockpit Environments
This paper proposes a Push-to-Talk Guided Gated Fusion (PTT-GGF) audio-visual multimodal architecture that significantly outperforms mainstream audio-only and cascaded schemes, providing a highly reliable and low-latency detection paradigm for smart cockpit monitoring systems.
Wei-Jun Pan, Qi-Xiang Wang, Yi-Di Wang et al.
· IEEE Access · 0 citations