Improving Human-Robot Communication in Noisy Environments with Visual Voice Activity Detection
Arunima Gopi Krishnan, Adrian Auer, Lisa Gutzeit
Editors: Josef F. Krems, Hugo Plácido da Silva, Pietro Cipresso
In Computer-Human Interaction Research and Applications - Proceedings, Part II, (CHIRA-2025), 20.10.-21.10.2025, Marbella, Springer Nature Switzerland, series Communications in Computer and Information Science, volume 2835, pages 71-91, Feb/2026. ISBN: 978-3-032-16451-3.
Zusammenfassung (Abstract)
:
This paper investigates the integration of Visual Voice Activity Detection (VVAD) into human robot dialogue systems to enhance communication in noisy environments. Usually, speech recognition systems often falter under acoustic interference, limiting their effectiveness in real-world human-robot interactions. By leveraging visual cues, especially lip movements, VVAD supports more accurate speech detection and turn-taking.
Stichworte
:
Human-Robot Interaction, Multimodal Dialogue, Speech Recognition, Visual Voice Activity Detection