Data Augmentation for End-to-end Code-switching Speech Recognition
This addresses the data scarcity issue for code-switching ASR, which is an incremental improvement in a domain-specific area.
The paper tackles the problem of limited code-switching data for end-to-end ASR by proposing three novel data augmentation approaches, resulting in a relative 24.0% reduction in WER compared to no augmentation and a 13.0% gain over SpecAugment alone.
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