Recently, SpecAugment, an augmentation scheme for automatic speech
recognition that acts directly on the spectrogram of input utterances, has
shown to be highly effective in enhancing the performance of end-to-end
networks on public datasets. In this paper, we demonstrate its effectiveness on
tasks with large scale datasets by investigating its application to the Google
Multidomain Dataset (Narayanan et al., 2018). We achieve improvement across all
test domains by mixing raw training data augmented with SpecAugment and
noise-perturbed training data when training the acoustic model. We also
introduce a modification of SpecAugment that adapts the time mask size and/or
multiplicity depending on the length of the utterance, which can potentially
benefit large scale tasks. By using adaptive masking, we are able to further
improve the performance of the Listen, Attend and Spell model on LibriSpeech to
2.2% WER on test-clean and 5.2% WER on test-other.

本文介绍了一种基于 SpecAugment 的自适应掩蔽方法，该方法可以直接作用于语音识别中输入语音信号的高频图谱上，并证明了该方法在大规模数据集上的有效性，通过将增强数据与噪声扰动训练的数据混合使用，使得模型在所有测试领域中都取得了进一步的提升。

大规模数据集上的 SpecAugment

SpecAugment on Large Scale Datasets

Deep neural networks provide state-of-the-art performance on various tasks
and are, therefore, widely used in real world applications. DNNs are becoming
frequently utilized in biometrics for extracting deep features, which can be
used in recognition systems for enrolling and recognizing new individuals. It
was revealed that deep neural networks suffer from a fundamental problem,
namely, they can unexpectedly misclassify examples formed by slightly
perturbing correctly recognized inputs. Various approaches have been developed
for generating these so-called adversarial examples, but they aim at attacking
end-to-end networks. For biometrics, it is natural to ask whether systems using
deep features are immune to or, at least, more resilient to attacks than
end-to-end networks. In this paper, we introduce a general technique called the
layerwise origin-target synthesis (LOTS) that can be efficiently used to form
adversarial examples that mimic the deep features of the target. We analyze and
compare the adversarial robustness of the end-to-end VGG Face network with
systems that use Euclidean or cosine distance between gallery templates and
extracted deep features. We demonstrate that iterative LOTS is very effective
and show that systems utilizing deep features are easier to attack than the
end-to-end network.

本研究通过引入层次原点目标合成技术（LOTS）提出了一般化的方法来生成称为对抗性样本的样本，研究比较了使用欧几里得距离和余弦距离的系统和 end-to-end VGG Face 网络的对抗鲁棒性，表明通过使用 LOTS 可以非常有效地攻击利用深度特征的系统，使其比 end-to-end 网络更容易受到攻击。