Multi-person speech interaction for tele-science experiments

Tele-science operation is an interactive way for scientists to carry out experiments in space payloads on the ground and is generally complicated and long waited. Meanwhile, speech interaction is one of the most efficient and convenient interaction ways. In this paper, we proposed a method of speech interaction that combines speech separation to solve tele-science interaction. Primarily, a speech separation method is proposed based on Deep Clustering with local optimization to achieve a better local separation and reduces the distortion of speech. Then, a tele-science interaction was constructed by combining speech recognition, semantic understanding and speech synthesis. The results show the proposed method make it possible to achieve a single-person tele-science interaction effectively and accurately and to accomplish a multi-person speech tele-science interaction through combining speech separation.