In this paper, we propose a domain adversarial training (DAT) algorithm to
alleviate the accented speech recognition problem. In order to reduce the
mismatch between labeled source domain data ("standard" accent) and unlabeled
target domain data (with heavy accents), we augment the learning objective for
a Kaldi TDNN network with a domain adversarial training (DAT) objective to
encourage the model to learn accent-invariant features. In experiments with
three Mandarin accents, we show that DAT yields up to 7.45% relative character
error rate reduction when we do not have transcriptions of the accented speech,
compared with the baseline trained on standard accent data only. We also find a
benefit from DAT when used in combination with training from automatic
transcriptions on the accented data. Furthermore, we find that DAT is superior
to multi-task learning for accented speech recognition.

本文提出了一个领域对抗训练算法（DAT）来缓解口音识别问题。我们将领域对抗训练（DAT）目标与 Kaldi TDNN 网络的学习目标相结合，鼓励模型学习不受口音影响的特征，以减少标准口音和带有口音的未标记目标域数据之间的不匹配。通过三种不同的普通话口音的实验，我们发现，与仅训练标准口音数据的基线相比，当我们没有口音转录时，DAT 可以使得字符错误率相对降低达 7.45％。我们还发现，DAT 与口音数据自动转录训练结合使用时具有优势，并且 DAT 比多任务学习在口音识别方面更为优异。