ISCA Archive Interspeech 2021
ISCA Archive Interspeech 2021

Fine-Grained Style Modeling, Transfer and Prediction in Text-to-Speech Synthesis via Phone-Level Content-Style Disentanglement

Daxin Tan, Tan Lee

This paper presents a novel design of neural network system for fine-grained style modeling, transfer and prediction in expressive text-to-speech (TTS) synthesis. Fine-grained modeling is realized by extracting style embeddings from the mel-spectrograms of phone-level speech segments. Collaborative learning and adversarial learning strategies are applied in order to achieve effective disentanglement of content and style factors in speech and alleviate the “content leakage” problem in style modeling. The proposed system can be used for varying-content speech style transfer in the single-speaker scenario. The results of objective and subjective evaluation show that our system performs better than other fine-grained speech style transfer models, especially in the aspect of content preservation. By incorporating a style predictor, the proposed system can also be used for text-to-speech synthesis. Audio samples are provided for system demonstration.


doi: 10.21437/Interspeech.2021-1129

Cite as: Tan, D., Lee, T. (2021) Fine-Grained Style Modeling, Transfer and Prediction in Text-to-Speech Synthesis via Phone-Level Content-Style Disentanglement. Proc. Interspeech 2021, 4683-4687, doi: 10.21437/Interspeech.2021-1129

@inproceedings{tan21_interspeech,
  author={Daxin Tan and Tan Lee},
  title={{Fine-Grained Style Modeling, Transfer and Prediction in Text-to-Speech Synthesis via Phone-Level Content-Style Disentanglement}},
  year=2021,
  booktitle={Proc. Interspeech 2021},
  pages={4683--4687},
  doi={10.21437/Interspeech.2021-1129}
}