The Phoneme Automatic Segmentation Algorithms Study of Tibetan Lhasa Words Continuous Speech Stream
- Jin-xi Zhang, Hong-zhi Yu, Ning Ma, Zhao-yao LI
- Corresponding Author
- Jin-xi Zhang
Available Online April 2013.
- https://doi.org/10.2991/icsem.2013.114How to use a DOI?
- Tibetan, Corpus, Phoneme automatic segmentation
- In this paper, we adopt two methods to voice phoneme segmentation when building Tibetan corpus: One is the traditional artificial segmentation method, one is the automatic segmentation method based on the Mono prime HMM model. And experiments are performed to analyze the accuracy of both methods of segmentations. The results showed: Automatic segmentation method based tone prime HMM model helps to shorten the cycle of building Tibetan corpus, especially in building a large corpus segmentation and labeling a lot of time and manpower cost savings, and have greatly improved the accuracy and consistency of speech corpus annotation information.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Jin-xi Zhang AU - Hong-zhi Yu AU - Ning Ma AU - Zhao-yao LI PY - 2013/04 DA - 2013/04 TI - The Phoneme Automatic Segmentation Algorithms Study of Tibetan Lhasa Words Continuous Speech Stream BT - 2nd International Conference On Systems Engineering and Modeling (ICSEM-13) PB - Atlantis Press SN - 1951-6851 UR - https://doi.org/10.2991/icsem.2013.114 DO - https://doi.org/10.2991/icsem.2013.114 ID - Zhang2013/04 ER -