Visual voice activity detection (V-VAD) plays an important role in both HCI and HRI, affecting both the conversation strategy and sync between humans and robots/computers. The typical speakingness decision of V-VAD consists of post-processing for signal smoothing and classiﬁcation using thresholding. Several parameters, ensuring a good trade-off between hit rate and false alarm, are usually heuristically deﬁned. This makes the V-VAD approaches vulnerable to noisy observation and changes of environment conditions, resulting in poor performance and robustness to undesired frequent speaking state changes. To overcome those difﬁculties, this paper proposes a new probabilistic approach, naming bi-level HMM and analyzing lip activity energy for V-VAD in HRI. The designing idea is based on lip movement and speaking assumptions, embracing two essential procedures into a single model.
A bi-level HMM is an HMM with two state variables in different levels, where state occurrence in a lower level conditionally depends on the state in an upper level. The approach works online with low-resolution image and in various lighting conditions, and has been successfully tested in 21 image sequences (22,927 frames). It achieved over 90% of probabilities of detection, in which it brought improvements of almost 20% compared to four other V-VAD approaches