# Referee: Towards reference-free cross-speaker style transfer with low-quality data for expressive speech synthesis

arXiv: https://arxiv.org/abs/2109.03439 · HTML: https://mlsanity.com/paper/2109.03439/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 8 Sep 2021.

## Builds on (most cited first, 18 of 18)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis](https://mlsanity.com/paper/1803.09017/) (2018)
- [Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron](https://mlsanity.com/paper/1803.09047/) (2018)
- [AdaSpeech: Adaptive Text to Speech for Custom Voice](https://mlsanity.com/paper/2103.00993/) (2021)
- [Hierarchical Generative Modeling for Controllable Speech Synthesis](https://mlsanity.com/paper/1810.07217/) (2018)
- [Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation](https://mlsanity.com/paper/2106.03153/) (2021)
- [Robust and fine-grained prosody control of end-to-end speech synthesis](https://mlsanity.com/paper/1811.02122/) (2018)
- [DurIAN: Duration Informed Attention Network For Multimodal Synthesis](https://mlsanity.com/paper/1909.01700/) (2019)
- [Fine-grained robust prosody transfer for single-speaker neural text-to-speech](https://mlsanity.com/paper/1907.02479/) (2019)
- [CopyCat: Many-to-Many Fine-Grained Prosody Transfer for Neural Text-to-Speech](https://mlsanity.com/paper/2004.14617/) (2020)
- [Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis](https://mlsanity.com/paper/2106.10831/) (2021)
- [Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis](https://mlsanity.com/paper/2107.12562/) (2021)
- [DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition](https://mlsanity.com/paper/1910.13282/) (2019)

## Abstract (arXiv)

Cross-speaker style transfer (CSST) in text-to-speech (TTS) synthesis aims at transferring a speaking style to the synthesised speech in a target speaker's voice. Most previous CSST approaches rely on expensive high-quality data carrying desired speaking style during training and require a reference utterance to obtain speaking style descriptors as conditioning on the generation of a new sentence. This work presents Referee, a robust reference-free CSST approach for expressive TTS, which fully leverages low-quality data to learn speaking styles from text. Referee is built by cascading a text-to-style (T2S) model with a style-to-wave (S2W) model. Phonetic PosteriorGram (PPG), phoneme-level pitch and energy contours are adopted as fine-grained speaking style descriptors, which are predicted from text using the T2S model. A novel pretrain-refinement method is adopted to learn a robust T2S model by only using readily accessible low-quality data. The S2W model is trained with high-quality target data, which is adopted to effectively aggregate style descriptors and generate high-fidelity speech in the target speaker's voice. Experimental results are presented, showing that Referee outperforms a global-style-token (GST)-based baseline approach in CSST.