Unsupervised and Semi-supervised Learning of Tone and Pitch Accent

@inproceedings{Levow2006UnsupervisedAS,
  title={Unsupervised and Semi-supervised Learning of Tone and Pitch Accent},
  author={Gina-Anne Levow},
  booktitle={HLT-NAACL},
  year={2006}
}
Recognition of tone and intonation is essential for speech recognition and language understanding. However, most approaches to this recognition task have relied upon extensive collections of manually tagged data obtained at substantial time and financial cost. In this paper, we explore two approaches to tone learning with substantially reductions in training data. We employ both unsupervised clustering and semi-supervised learning to recognize pitch accent in English and tones in Mandarin… CONTINUE READING
Highly Cited
This paper has 33 citations. REVIEW CITATIONS
23 Citations
25 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 25 references

Neural-network simulation of tonal categorization based on f0 velocity profiles

  • Bruno Gauthier, Rushen Shi, Yi Xu, Robert Proulx.
  • Journal of the Acoustical Society of America, 117…
  • 2005
1 Excerpt

New methods for spectral clustering

  • I. Fischer, J. Poland.
  • Technical Report ISDIA-12-04, IDSIA.
  • 2004
3 Excerpts

New methods for spectral clustering . Technical Report ISDIA - 1204 , IDSIA . H . Fujisaki . 1983 . Dynamic characteristics of voice fundamental frequency in speech and singing

  • Bruno Gauthier, Rushen Shi, Yi Xu, Robert Proulx
  • The Production of Speech
  • 2004

Similar Papers

Loading similar papers…