# Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS

arXiv: https://arxiv.org/abs/2106.10003 · HTML: https://mlsanity.com/paper/2106.10003/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2021.

## Built on by (most cited first, 6 of 6)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Cross-speaker style transfer for text-to-speech using data augmentation](https://mlsanity.com/paper/2202.05083/) (2022)
- [Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis](https://mlsanity.com/paper/2212.06397/) (2022)
- [Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis](https://mlsanity.com/paper/2303.07711/) (2023)
- [VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing](https://mlsanity.com/paper/2408.05758/) (2024)
- [PoeticTTS -- Controllable Poetry Reading for Literary Studies](https://mlsanity.com/paper/2207.05549/) (2022)

## Abstract (arXiv)

End-to-end neural TTS training has shown improved performance in speech style transfer. However, the improvement is still limited by the training data in both target styles and speakers. Inadequate style transfer performance occurs when the trained TTS tries to transfer the speech to a target style from a new speaker with an unknown, arbitrary style. In this paper, we propose a new approach to style transfer for both seen and unseen styles, with disjoint, multi-style datasets, i.e., datasets of different styles are recorded, each individual style is by one speaker with multiple utterances. To encode the style information, we adopt an inverse autoregressive flow (IAF) structure to improve the variational inference. The whole system is optimized to minimize a weighed sum of four different loss functions: 1) a reconstruction loss to measure the distortions in both source and target reconstructions; 2) an adversarial loss to "fool" a well-trained discriminator; 3) a style distortion loss to measure the expected style loss after the transfer; 4) a cycle consistency loss to preserve the speaker identity of the source after the transfer. Experiments demonstrate, both objectively and subjectively, the effectiveness of the proposed approach for seen and unseen style transfer tasks. The performance of the new approach is better and more robust than those of four baseline systems of the prior art.