Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/SLT48900.2021.9383620 | 2021 IEEE Spoken Language Technology Workshop (SLT) |
Keywords | DocType | ISSN |
end-to-end speech recognition,code-switching,data augmentation,text-to-speech | Conference | 2639-5479 |
ISBN | Citations | PageRank |
978-1-7281-7067-1 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chenpeng Du | 1 | 0 | 1.69 |
Hao Li | 2 | 261 | 85.92 |
Yizhou Lu | 3 | 1 | 3.72 |
Lan Wang | 4 | 0 | 0.68 |
Yanmin Qian | 5 | 295 | 44.44 |