@inproceedings{aylett2014flexible,
  title={A Flexible Front-End for {HTS}},
  author={Aylett, Matthew P. and Dall, Rasmus and Ghoshal, Arnab and Henter, Gustav Eje and Merritt, Thomas},
  booktitle={Proc. Interspeech},
  abstract={Parametric speech synthesis techniques depend on full context acoustic models generated by language front-ends, which analyse linguistic and phonetic structure. HTS, the leading parametric synthesis system, can use a number of different front-ends to generate full context models for synthesis and training. In this paper we explore the use of a new text processing front-end that has been added to the speech recognition toolkit Kaldi as part of an ongoing project to produce a new parametric speech synthesis system, Idlak. The use of XML specification files, a modular design, and modern coding and testing approaches, make the Idlak front-end ideal for adding, altering and experimenting with the contexts used in full context acoustic models. The Idlak front-end was evaluated against the standard Festival front-end in the HTS system. Results from the Idlak front-end compare well with the more mature Festival front-end (Idlak - 2.83 MOS vs Festival - 2.85 MOS), although a slight reduction in naturalness perceived by non-native English speakers can be attributed to Festival's insertion of non-punctuated pauses.},
  keywords={speech synthesis, text processing, parametric synthesis, Kaldi, Idlak},
  address={Singapore},
  month={Sept.},
  publisher={ISCA},
  volume={15},
  pages={1283--1287},
  doi={10.21437/Interspeech.2014-320},
  year={2014}
}