Mandarin-English Code-switching Speech Recognition

Haihua Xu, Van Tung Pham, Zin Tun Kyaw, Zhi Hao Lim, Eng Siong Chng, Haizhou Li


This work presents the development of a Mandarin-English code-switching speech recognition system. We demonstrate three key novelties in our system. First, we increase our lexicon coverage to 360K words, where phone sets of different languages are maintained separately. Secondly, we used over 1000 hours of training data combining both mono-lingual and code-switch corpus to develop the acoustic model. Finally, for language modelling, we applied context-aware text normalization and word-class language model. When testing on our internal code-switch close talk microphone recording, the system achieves recognition performance that can support real applications.


Cite as: Xu, H., Pham, V.T., Kyaw, Z.T., Lim, Z.H., Chng, E.S., Li, H. (2018) Mandarin-English Code-switching Speech Recognition. Proc. Interspeech 2018, 554-555.


@inproceedings{Xu2018,
  author={Haihua Xu and Van Tung Pham and Zin Tun Kyaw and Zhi Hao Lim and Eng Siong Chng and Haizhou Li},
  title={Mandarin-English Code-switching Speech Recognition},
  year=2018,
  booktitle={Proc. Interspeech 2018},
  pages={554--555}
}