论文标题
端到端代码转换语音识别的数据增强
Data Augmentation for End-to-end Code-switching Speech Recognition
论文作者
论文摘要
培训端到端自动语音识别（ASR）模型通常需要大量数据，而代码转换数据通常受到限制。在本文中，提出了三种新颖的方法来扩展代码转换数据。具体来说，它们是使用现有代码转换数据的音频拼接，而TTS则具有由单词翻译或单词插入生成的新代码转换文本。我们在200小时的普通话 - 英语密码开关数据集中进行的实验表明，所有三种提出的方法都会单独地对ASR进行大幅改进。此外，所有提出的方法都可以与最近的流行规格结合使用，并且可以获得添加的增益。与该系统相比，相对相比，相对24.0％显着降低了，而没有任何数据扩展，而与系统相比，相对增长率仍然为13.0％
Training a code-switching end-to-end automatic speech recognition (ASR) model normally requires a large amount of data, while code-switching data is often limited. In this paper, three novel approaches are proposed for code-switching data augmentation. Specifically, they are audio splicing with the existing code-switching data, and TTS with new code-switching texts generated by word translation or word insertion. Our experiments on 200 hours Mandarin-English code-switching dataset show that all the three proposed approaches yield significant improvements on code-switching ASR individually. Moreover, all the proposed approaches can be combined with recent popular SpecAugment, and an addition gain can be obtained. WER is significantly reduced by relative 24.0% compared to the system without any data augmentation, and still relative 13.0% gain compared to the system with only SpecAugment
