ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Language identification on code-switching utterances using multiple cues

Dau-Cheng Lyu, Ren-Yuan Lyu

Code-switching speech is an utterance containing two or more languages. Usually, the switching linguistic unit is in clause or word levels. In this paper, a two-stage framework is proposed, containing a language identifier and then a speech recognizer, to evaluate on a Mandarin-Taiwanese code-switching utterance. In the language identifier, we use multiple cues including acoustic, prosodic and phonetic features. In order to integrate the cues to distinguish one language from another, we used a maximum a posteriori decision rule to connect an acoustic model, a duration model and a language model. In the experiments, we have achieved 34.5% (LID) and 17.7% (ASR) error rate reduction comparing with one stage LVCSR-based system.


doi: 10.21437/Interspeech.2008-223

Cite as: Lyu, D.-C., Lyu, R.-Y. (2008) Language identification on code-switching utterances using multiple cues. Proc. Interspeech 2008, 711-714, doi: 10.21437/Interspeech.2008-223

@inproceedings{lyu08_interspeech,
  author={Dau-Cheng Lyu and Ren-Yuan Lyu},
  title={{Language identification on code-switching utterances using multiple cues}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={711--714},
  doi={10.21437/Interspeech.2008-223}
}