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

arXiv: https://arxiv.org/abs/2011.03943 · HTML: https://mlsanity.com/paper/2011.03943/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2020.

## Built on by (most cited first, 5 of 5)

- [Emotion Intensity and its Control for Emotional Voice Conversion](https://mlsanity.com/paper/2201.03967/) (2022)
- [Speech Synthesis with Mixed Emotions](https://mlsanity.com/paper/2208.05890/) (2022)
- [Fine-grained style control in Transformer-based Text-to-speech Synthesis](https://mlsanity.com/paper/2110.06306/) (2021)
- [CorrTalk: Correlation Between Hierarchical Speech and Facial Activity Variances for 3D Animation](https://mlsanity.com/paper/2310.11295/) (2023)
- [Controllable speech synthesis by learning discrete phoneme-level prosodic representations](https://mlsanity.com/paper/2211.16307/) (2022)

## Abstract (arXiv)

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 https://daxintan-cuhk.github.io/pl-csd-speech .