@InProceedings{takeda-komatani:2017:I17-1,
  author    = {Takeda, Ryu  and  Komatani, Kazunori},
  title     = {Unsupervised Segmentation of Phoneme Sequences based on Pitman-Yor Semi-Markov Model using Phoneme Length Context},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {243--252},
  abstract  = {Unsupervised segmentation of phoneme sequences is an essential process to
	obtain unknown words during spoken dialogues. 
	In this segmentation, an input phoneme sequence without delimiters is converted
	into segmented sub-sequences corresponding to words.
	The Pitman-Yor semi-Markov model (PYSMM) is promising for this problem, but its
	performance degrades when it is applied to phoneme-level word segmentation. 
	This is because of insufficient cues for the segmentation, e.g., homophones are
	improperly treated as single entries and their different contexts are also
	confused. 
	We propose a phoneme-length context model for PYSMM to give a helpful cue at
	the phoneme-level and to predict succeeding segments more accurately. 
	Our experiments showed that the peak performance with our context model
	outperformed those without such a context model by 0.045 at most in terms of
	F-measures of estimated segmentation.},
  url       = {http://www.aclweb.org/anthology/I17-1025}
}