IPA: improved phone modelling with recurrent neural networks

This paper describes phone modelling improvements t o the hybrid ronnectionist-hidden Markov model speech recognition system developed a t Cambridge University. These improvements are applied to phone recognition from the TIMIT task and word recognition from the Wall Street Journal (WSJ) task. A recurrent net is used to map acoustic vectors t o posterior probabilities of phone classes. The maximum likelihood phone or word string is then extracted using Markov models. The paper describes three improvements: ronnectionist model merging; explicit. presentation of acoustic context; and improved duration modelling. The first is shown to provide a significant improvement in the TIMIT phone recognition rate and all three provide an improvement in the WSJ word recognition rate.