A context-sensitive homograph disambiguation in Thai text-to-speech synthesis
NAACL-Short '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: companion volume of the Proceedings of HLT-NAACL 2003--short papers - Volume 2
Thai speech processing technology: A review
Speech Communication
Digital storytelling book generator with customizable synthetic voice styles
Proceedings of the 4th International Convention on Rehabilitation Engineering & Assistive Technology
Hi-index | 0.00 |
DAISY is the current standard for Digital Talking Books (DTBs) authored in many countries, including Thailand. Still, the number of book titles available in the form of DTB is limited partly due to their time-consuming production process. Although DTB authoring tools capable of producing Audio/Full Text DTBs are widely available, they do not fully support Thai, a language in which text segmentation cannot be performed straight-forwardly. In this work, we propose a DTB authoring tool called ChulaDAISY to be used for producing DTBs whose contents contain Thai texts, either manually or automatically. The program is also capable of uploading the finished DTBs through its GUI onto its online DTB archiving system where DTBs can be downloaded via web browsers. This consideration aims at tackling possible difficulties in commuting to libraries by the blinds. Experiments are conducted in order to evaluate the usability of the program as well as to measure the DTB production rate using ChulaDAISY in comparison to the one following a traditional procedure. We have found that ChulaDAISY yields an approximately 35% improvement in productivity over the traditional procedure.