Building a Natural Sounding Text-to-Speech System for the Nepali Language - Research and Development Challenges and Solutions

Roop Bajracharya, Santosh Regmi, Bal Krishna Bal, Balaram Prasain


´╗┐Text-to-Speech (TTS) synthesis has come far from its primitive synthetic monotone voices to more natural and intelligible sounding voices. One of the direct applications of natural bounding TTS systems is the screen reader applications for the visually impaired and the blind community. The Festival Speech Synthesis System uses a concatenative speech synthesis method together with the unit selection process to generate a natural sounding voice. This work primarily gives an account of the efforts put towards developing a Natural sounding TTS system for Nepali using the Festival system. We also shed light on the issues faced and the solutions derived which can be quite overlapping across other similar under-resourced languages in the region.


 DOI: 10.21437/SLTU.2018-32

Cite as: Bajracharya, R., Regmi, S., Bal, B.K., Prasain, B. (2018) Building a Natural Sounding Text-to-Speech System for the Nepali Language - Research and Development Challenges and Solutions. Proc. The 6th Intl. Workshop on Spoken Language Technologies for Under-Resourced Languages, 152-156, DOI: 10.21437/SLTU.2018-32.


@inproceedings{Bajracharya2018,
  author={Roop Bajracharya and Santosh Regmi and Bal Krishna Bal and Balaram Prasain},
  title={{Building a Natural Sounding Text-to-Speech System for the Nepali Language - Research and Development Challenges and Solutions}},
  year=2018,
  booktitle={Proc. The 6th Intl. Workshop on Spoken Language Technologies for Under-Resourced Languages},
  pages={152--156},
  doi={10.21437/SLTU.2018-32},
  url={http://dx.doi.org/10.21437/SLTU.2018-32}
}