Training Augmentation with Adversarial Examples for Robust Speech
Recognition
release_6vmxpmfbmzb3pjkvk6sbb3u4gm
by
Sining Sun, Ching-Feng Yeh, Mari Ostendorf, Mei-Yuh Hwang, Lei Xie
2018
Abstract
This paper explores the use of adversarial examples in training speech
recognition systems to increase robustness of deep neural network acoustic
models. During training, the fast gradient sign method is used to generate
adversarial examples augmenting the original training data. Different from
conventional data augmentation based on data transformations, the examples are
dynamically generated based on current acoustic model parameters. We assess the
impact of adversarial data augmentation in experiments on the Aurora-4 and
CHiME-4 single-channel tasks, showing improved robustness against noise and
channel variation. Further improvement is obtained when combining adversarial
examples with teacher/student training, leading to a 23% relative word error
rate reduction on Aurora-4.
In text/plain
format
Archived Content
There are no accessible files associated with this release. You could check other releases for this work for an accessible version.
Know of a fulltext copy of on the public web? Submit a URL and we will archive it
1806.02782v2
access all versions, variants, and formats of this works (eg, pre-prints)