# Multi-Reference Neural TTS Stylization with Adversarial Cycle Consistency

arXiv: https://arxiv.org/abs/1910.11958 · HTML: https://mlsanity.com/paper/1910.11958/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2019.

## Built on by (most cited first, 12 of 12)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [V2C: Visual Voice Cloning](https://mlsanity.com/paper/2111.12890/) (2021)
- [The Ethical Implications of Generative Audio Models: A Systematic Literature Review](https://mlsanity.com/paper/2307.05527/) (2023)
- [Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis](https://mlsanity.com/paper/2107.12562/) (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)
- [Review of end-to-end speech synthesis technology based on deep learning](https://mlsanity.com/paper/2104.09995/) (2021)
- [Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTS](https://mlsanity.com/paper/2207.06000/) (2022)
- [DiCLET-TTS: Diffusion Model based Cross-lingual Emotion Transfer for Text-to-Speech -- A Study between English and Mandarin](https://mlsanity.com/paper/2309.00883/) (2023)
- [Improving Cross-lingual Speech Synthesis with Triplet Training Scheme](https://mlsanity.com/paper/2202.10729/) (2022)
- [A Discourse-level Multi-scale Prosodic Model for Fine-grained Emotion Analysis](https://mlsanity.com/paper/2309.11849/) (2023)
- [Towards Cross-speaker Reading Style Transfer on Audiobook Dataset](https://mlsanity.com/paper/2208.05359/) (2022)

## Abstract (arXiv)

Current multi-reference style transfer models for Text-to-Speech (TTS) perform sub-optimally on disjoints datasets, where one dataset contains only a single style class for one of the style dimensions. These models generally fail to produce style transfer for the dimension that is underrepresented in the dataset. In this paper, we propose an adversarial cycle consistency training scheme with paired and unpaired triplets to ensure the use of information from all style dimensions. During training, we incorporate unpaired triplets with randomly selected reference audio samples and encourage the synthesized speech to preserve the appropriate styles using adversarial cycle consistency. We use this method to transfer emotion from a dataset containing four emotions to a dataset with only a single emotion. This results in a 78% improvement in style transfer (based on emotion classification) with minimal reduction in fidelity and naturalness. In subjective evaluations our method was consistently rated as closer to the reference style than the baseline. Synthesized speech samples are available at: https://sites.google.com/view/adv-cycle-consistent-tts