Automatic speech recognition using hidden Markov models and artificial neural networks

An algorithm is presented for isolated-word recognition, taking into consideration the duration variability of the different utterances of the same word. The algorithm is based on extracting acoustical features from the speech signal and using them as the input to multilayer perceptrons neural networks. The backpropagation algorithm is used to train the networks. The hidden Markov model (HMM) is implemented to extract temporal features (states) from the speech signal. The input vector to the network consists of 16 cepstral coefficients, two delta cepstral coefficients, and five elements to represent the state. The networks are trained to recognize the correct words and to reject the wrong words. The training set consists of ten words (digit zero to digit nine), each uttered seven times, by three different speakers. The test set consists of three utterances of each of the ten words. The authors´ results show the ability to recognize all of these words