ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

Prediction of prosodic phrase boundaries using stochastic context-free grammar

Shigeru Fujio, Yoshinori Sagisaka, Norio Higuchi

We propose a method of predicting prosodic phrase boundaries using a SCFG (stochastic context-free grammar) for non-bracketed input word attributes. In this paper, prosodic phrase boundaries are predicted using information generated by a SCFG trained using phrase dependency bracketings and prosody bracketings. Using the Inside-Outside algorithm for training, corpora with phrase dependency brackets are first used to train the SCFG from scratch. Next, this SCFG is re-trained using the same corpora with prosody brackets. Then, the probability of each bracketing structure is computed using the SCFG, and is used as a parameter in the prediction of the prosodic phrase boundaries. To examine the effect of these parameters, prosodic phrase boundaries were predicted. Held-out data: 92.9% of the prosodic phrase boundaries, and 83.1% of the non-prosodic phrase boundaries, were correctly predicted.


Cite as: Fujio, S., Sagisaka, Y., Higuchi, N. (1994) Prediction of prosodic phrase boundaries using stochastic context-free grammar. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 839-842

@inproceedings{fujio94_icslp,
  author={Shigeru Fujio and Yoshinori Sagisaka and Norio Higuchi},
  title={{Prediction of prosodic phrase boundaries using stochastic context-free grammar}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={839--842}
}