Continuous Speech Recognition: Preprocessing, Feature Selection, Speech Recognition and Segmentation

Continuous speech recognition is a great challenge in this beginning of the century. The impressive advances in hardware allow the use of sophisticated mathematical methods to solve complex problems. In this work, we show that methods invented for solving long constraint length convolutional codes can be used in speech recognition. The main contributions of this work can be summarized as follows: -The applicability of the stack decoding algorithm to continuous speech recognition. -The development and the analysis of a path metric based on the Mahalanobis distance. It has been used in the implementation of the stack algorithm in recognition program and also in the Viterbi algorithm in the training program. -The development of a novel algorithm for clipped speech restoration based on linear prediction. -Speech denoising method based on time varying Wiener filters. We obtained remarkable results using a very low order filter. -We have shown that the MFCC set is nearly Gaussian and provides the best separability between classes as compared with LPC and PARCOR coefficients. -Finally, we have developed an automatic segmentation algorithm that we use for training the system.