Text to phoneme alignment and mapping for speech technology: A neural networks approach

Abstract

A common problem in speech technology is the alignment of representations of text and phonemes, and the learning of a mapping between them that generalizes well to unseen inputs. The state-of-the-art technology appears to be symbolic rule-based systems, which is surprising given the number of neural network systems for text to phoneme mapping that have been developed over the years. This paper explores why that may be the case, and demonstrates that it is possible for neural networks to simultaneously perform text to phoneme alignment and mapping with performance levels at least comparable to the best existing systems.