Deep Recurrent Neural Networks for Acoustic Modelling
Machine Learning
2015-04-08 v1 Computation and Language
Neural and Evolutionary Computing
Machine Learning
Abstract
We present a novel deep Recurrent Neural Network (RNN) model for acoustic modelling in Automatic Speech Recognition (ASR). We term our contribution as a TC-DNN-BLSTM-DNN model, the model combines a Deep Neural Network (DNN) with Time Convolution (TC), followed by a Bidirectional Long Short-Term Memory (BLSTM), and a final DNN. The first DNN acts as a feature processor to our model, the BLSTM then generates a context from the sequence acoustic signal, and the final DNN takes the context and models the posterior probabilities of the acoustic states. We achieve a 3.47 WER on the Wall Street Journal (WSJ) eval92 task or more than 8% relative improvement over the baseline DNN models.
Cite
@article{arxiv.1504.01482,
title = {Deep Recurrent Neural Networks for Acoustic Modelling},
author = {William Chan and Ian Lane},
journal= {arXiv preprint arXiv:1504.01482},
year = {2015}
}