A segmentation method for noisy speech using genetic algorithm

The paper presents a technique to segment automatically a speech signal in noisy environments. The speech segmentation is formulated as an optimization problem and boundaries of the speech segments are detected using a genetic algorithm (GA). The initial number of segments is estimated from the modified version of the signal using the minimal number of binary Walsh basis functions. The segmentation results are improved through the generations of the GA by introducing a new evaluation function, which is based on the sample entropy and a heterogeneity measure. Experiments have been carried out on the TIDIGITS database with different types and levels of noise; the results show the efficiency of the proposed genetic segmentation algorithm.