We describe the latest improvements to the IBM English conversational telephone speech recognition system. Some of the techniques that were found beneficial are: maxout networks with annealed dropout rates; networks with a very large number of outputs trained on 2000 hours of data; joint modeling of partially unfolded recurrent neural networks and convolutional nets by combining the bottleneck and output layers and retraining the resulting model; and lastly, sophisticated language model rescoring with exponential and neural network LMs. These techniques result in an 8.0% word error rate on the Switchboard part of the Hub5-2000 evaluation test set which is 23% relative better than our previous best published result.
@article{arxiv.1505.05899,
title = {The IBM 2015 English Conversational Telephone Speech Recognition System},
author = {George Saon and Hong-Kwang J. Kuo and Steven Rennie and Michael Picheny},
journal= {arXiv preprint arXiv:1505.05899},
year = {2015}
}