Neural networks for feature computations in automatic speech recognition
Stephen A. Zahorian, David Livingston · 2003
Neural networks (NNs) are used for defining good features to use in automatic speech recognition. Of several approaches investigated, the best results were obtained using a NN as a memoryless nonlinear transformation to transform acoustic speech features to a continuous-valued phonetic feature space. The goal is to use labeled training data to automatically derive features which will enhance machine speech recognition. The transformed features were experimentally tested in a syllable recognition task using a hidden Markov model for speech recognition. Syllable recognition rates using the NN-derived features were comparable to those obtained using features derived from a linear transformation.>