Barge-in-able robot audition based on ICA and missing feature theory under semi-blind situation

This paper describes a robot audition system that allows the user to barge-in; that is, the user can speak simultaneously when the robot is speaking. Our "barge-in-able" system consists of two stages: (1) cancellation of robot speech and (2) recognition of the separated user speech under the "semi-blind situation". The semi-blind situation is where a robot's speech signal is known but a user's speech signal is not. The first stage is achieved by using an adaptive filter based on time-frequency domain Independent Component Analysis, because that can separate robot speech more robustly against noise than conventional echo cancellers. To improve performance in online processing, we utilized known source normalization and the exponentially weighted stepsize method. The second stage is achieved by automatic speech recognition (ASR) based on the missing feature theory which provides robust recognition by exploiting the reliability of speech features distorted due to noise and/or separation. The semi-blind situation simplifies the estimation of such reliabilities. Experiments demonstrated that our system improved word correctness of ASR by 10.0 %.