ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

The CMU-interACT 2008 Mandarin transcription system

Roger Hsiao, Mark Fuhs, Yik-Cheung Tam, Qin Jin, Tanja Schultz

We present our Mandarin BN/BC transcription system recently developed for the GALE07 evaluation. The system employs a 3-pass decoding strategy trained with over 1300 hours of quickly transcribed audio. We successfully apply discriminative training, dynamic unsupervised language model adaptation, and system combination techniques in our system. We furthermore achieve improvements by combining an Initial-Final system with a genre dependent phone system. On the GALE07 phase 2 retest evaluation, our system achieves a character error rate(CER) of 13.3% on dev07 test set and 13.5% on eval07 unsequestered test set. Our system also allows combination with other sites and in this paper, we investigate different system combination strategies which significantly improve the final recognition performance.

doi: 10.21437/Interspeech.2008-417

Cite as: Hsiao, R., Fuhs, M., Tam, Y.-C., Jin, Q., Schultz, T. (2008) The CMU-interACT 2008 Mandarin transcription system. Proc. Interspeech 2008, 1445-1448, doi: 10.21437/Interspeech.2008-417

  author={Roger Hsiao and Mark Fuhs and Yik-Cheung Tam and Qin Jin and Tanja Schultz},
  title={{The CMU-interACT 2008 Mandarin transcription system}},
  booktitle={Proc. Interspeech 2008},