Human-robot interface using robust speech recognition and user localization based on noise separation device

This paper introduces a robust human-robot interface (HRI) system using a speech recognition and a user localization. For a robust speech recognition indoors under unknown noises and acoustic reverberations, a blind source separation (BSS) algorithm is implemented by a block-wise processing and developed using digital signal processing board to guarantee real-time operation. And a reverberation-robust sound source localization algorithm using separated signals is proposed. Although the BSS method cannot completely preserve the room acoustic information, the proposed localization algorithm overcomes this problem using target channel selection and target-emphasized enhancement methods. The developed algorithms are integrated into the commercial robot system to provide overall voice-enabled HRI. A series of tests are conducted to evaluate the performance of the BSS-based speech recognition and user localization method, and the results show a remarkable performance even under severe non-stationary noise conditions.