In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features (e.g., mel-spectrograms or MFCC) as the input, and recognizing both text sequences, where the two recognition losses use the same combination weight. We apply MixSpeech on two popular end-to-end speech recognition models including LAS (Listen, Attend and Spell) and Transformer, and conduct experiments on several low-resource datasets including TIMIT, WSJ, and HKUST. Experimental results show that MixSpeech achieves better accuracy than the baseline models without data augmentation, and outperforms a strong data augmentation method SpecAugment on these recognition tasks. Specifically, MixSpeech outperforms SpecAugment with a relative PER improvement of 10.6$\%$ on TIMIT dataset, and achieves a strong WER of 4.7$\%$ on WSJ dataset.

中文翻译：

---

MixSpeech：用于低资源自动语音识别的数据增强

在本文中，我们提出了MixSpeech，这是一种基于混合的自动语音识别（ASR）的简单而有效的数据增强方法。MixSpeech通过将两个不同语音特征（例如，梅尔声谱图或MFCC）的加权组合作为输入，并识别两个文本序列（其中两个识别损失使用相同的组合权重）来训练ASR模型。我们在两种流行的端到端语音识别模型（包括LAS（听，出席和拼写）和Transformer）上应用MixSpeech，并在TIMIT，WSJ和HKUST等几种低资源数据集上进行了实验。实验结果表明，MixSpeech比没有数据增强的基线模型具有更高的准确性，并且在这些识别任务上优于强大的数据增强方法SpecAugment。具体来说，