Posterior-Based Features and Distances in Template Matching for Speech Recognition

摘要

The use of large speech corpora in example-based approaches for speech recognition is mainly focused on increasing the number of examples. This strategy presents some difficulties because databases may not provide enough examples for some rare words. In this paper we present a different method to incorporate the information contained in such corpora in these example-based systems. A multilayer perceptron is trained on these databases to estimate speaker and task-independent phoneme posterior probabilities, which are used as speech features. By reducing the variability of features, fewer examples are needed to properly characterize a word. In this way, performance can be highly improved when limited number of examples is available. Moreover, we also study posterior-based local distances, these result more effective than traditional Euclidean distance. Experiments on Phonebook database support the idea that posterior features with a proper local distance can yield competitive results.