Unsupervised Segmentation of Phoneme Sequences based on Pitman-Yor Semi-Markov Model using Phoneme Length Context

Ryu Takeda, Kazunori Komatani


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.
Anthology ID:
I17-1025
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
243–252
Language:
URL:
https://aclanthology.org/I17-1025
DOI:
Bibkey:
Cite (ACL):
Ryu Takeda and Kazunori Komatani. 2017. Unsupervised Segmentation of Phoneme Sequences based on Pitman-Yor Semi-Markov Model using Phoneme Length Context. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 243–252, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Unsupervised Segmentation of Phoneme Sequences based on Pitman-Yor Semi-Markov Model using Phoneme Length Context (Takeda & Komatani, IJCNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/I17-1025.pdf