Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS

Haohan Guo, Frank K. Soong, Lei He, Lei Xie


The end-to-end TTS, which can predict speech directly from a given sequence of graphemes or phonemes, has shown improved performance over the conventional TTS. However, its predicting capability is still limited by the acoustic/phonetic coverage of the training data, usually constrained by the training set size. To further improve the TTS quality in pronunciation, prosody and perceived naturalness, we propose to exploit the information embedded in a syntactically parse tree where the inter-phrase/word information of a sentence is organized in a multilevel tree structure. Specifically, two key features: phrase structure and relations between adjacent words are investigated. Experimental results in subjective listening, measured on three test sets, show that the proposed approach is effective to improve the pronunciation clarity, prosody and naturalness of the synthesized speech of the baseline system.


 DOI: 10.21437/Interspeech.2019-2167

Cite as: Guo, H., Soong, F.K., He, L., Xie, L. (2019) Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS. Proc. Interspeech 2019, 4460-4464, DOI: 10.21437/Interspeech.2019-2167.


@inproceedings{Guo2019,
  author={Haohan Guo and Frank K. Soong and Lei He and Lei Xie},
  title={{Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={4460--4464},
  doi={10.21437/Interspeech.2019-2167},
  url={http://dx.doi.org/10.21437/Interspeech.2019-2167}
}