Improved Mandarin Speech Recognition by Lattice Rescoring with Enhanced Tone Models

@inproceedings{Wang2006ImprovedMS,
  title={Improved Mandarin Speech Recognition by Lattice Rescoring with Enhanced Tone Models},
  author={Huanliang Wang and Yao Qian and Frank K. Soong and Jian-Lai Zhou and Jiqing Han},
  booktitle={ISCSLP},
  year={2006}
}
Tone plays an important lexical role in spoken tonal languages like Mandarin Chinese. In this paper we propose a two-pass search strategy for improving tonal syllable recognition performance. In the first pass, instantaneous F0 information is employed along with corresponding cepstral information in a 2-stream HMM based decoding. The F0 stream, which incorporates both discrete voiced/unvoiced information and continuous F0 contour, is modeled with a multi-space distribution. With just the first… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 11 references

Use of Tone Information in Cantonese LVCSR Based on Generalized Character Posterior Probability Decoding

  • Y. Qian
  • PhD. Thesis, CUHK,
  • 2005
3 Excerpts

Lexical Stress Recognitio Using Hidden Markov Models

  • G. J. Freij, F. Fallside
  • Proc . ICASSP
  • 1988

Similar Papers

Loading similar papers…