Adaptive Noise Reduction and Voice Activity Detection for improved Verbal Human-Robot Interaction using Binaural Data

• DOI: 10.1109/robot.2007.363580
• Publication Date: 2007-06-07T16:09:21Z
• Authors: Robert Brueckmann; Andrea Scheidig; Horst-Michael Gross
• Keywords: Human–robot interaction; Human voice

Speech has become an important part in human robot interaction (HRI), e.g. for person detection systems by using localized sound sources or applications automatic speech recognition (ASR) systems. By HRI real world environments, we have to deal with mostly high and varying background noise, reverberation also different superimposing other noises. Therefore, scenarios a suitable signal preprocessing is essential. In this paper, present of the artificial auditory system implemented on mobile HOROS only two low cost microphones. We combined neural voice activity (VAD) adaptive noise reduction which are essential aspects changing populated real-world environments. result, our able robustly react signals from its partner while ignoring sources. Experiments show significantly improved ASR performance demanding environments making use scenarios.