Hands-free speech recognition and communication on PDAs using microphone array technology

In this paper, a personal digital assistant (PDA) for hands-free speech recognition and communication with a microphone array mounted on the PDA is presented. An outlier-robust generalized sidelobe canceller (RGSC) and a minimum mean-squared error (MMSE) estimator for log Mel-spectral energy coefficients using a Gaussian mixture model (GMM) for clean speech are implemented in real-time and evaluated for speech recognition based on a small experimental multichannel database. It is shown that the joint system of beamformer and single-channel noise suppression highly improves the noise-robustness of a large-vocabulary speech recognizer so that down to SNR = 5 dB more than 91% word accuracy is obtained