The "Voice Command" system. designed for isolated word recognition tasks in real-world noisy environments. was implemented on a fixed-point DSP board to operate in real-time. Simple auditory model, ie., zero-crossings with peak amplitudes (ZCPA) model, is used for noise-robust feature extraction, and neural network classifier recognizes input patterns.The system performance is further improved by incorporating speaker adaptation and out-of-vocabulary word rejection capabilities. The radial basis function (RBF) classifier provides better sefjection performance than multi-layer perceptron (MLP) classifiers.
展开▼