# Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis

arXiv: https://arxiv.org/abs/2108.02271 · HTML: https://mlsanity.com/paper/2108.02271/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2021.

## Built on by (most cited first, 10 of 10)

- [Avocodo: Generative Adversarial Network for Artifact-free Vocoder](https://mlsanity.com/paper/2206.13404/) (2022)
- [Model See Model Do: Speech-Driven Facial Animation with Style Control](https://mlsanity.com/paper/2505.01319/) (2025)
- [DiEmo-TTS: Disentangled Emotion Representations via Self-Supervised Distillation for Cross-Speaker Emotion Transfer in Text-to-Speech](https://mlsanity.com/paper/2505.19687/) (2025)
- [Voice Cloning: Comprehensive Survey](https://mlsanity.com/paper/2505.00579/) (2025)
- [Controllable Speaking Styles Using a Large Language Model](https://mlsanity.com/paper/2305.10321/) (2023)
- [Multi-interaction TTS toward professional recording reproduction](https://mlsanity.com/paper/2507.00808/) (2025)
- [MultiVerse: Efficient and Expressive Zero-Shot Multi-Task Text-to-Speech](https://mlsanity.com/paper/2410.03192/) (2024)
- [Daisy-TTS: Simulating Wider Spectrum of Emotions via Prosody Embedding Decomposition](https://mlsanity.com/paper/2402.14523/) (2024)
- [A Human-in-the-Loop Approach to Improving Cross-Text Prosody Transfer](https://mlsanity.com/paper/2406.06601/) (2024)
- [A survey of AI-generated voices and their detection](https://mlsanity.com/paper/2608.15411/) (2026)

## Abstract (arXiv)

This paper presents Daft-Exprt, a multi-speaker acoustic model advancing the state-of-the-art for cross-speaker prosody transfer on any text. This is one of the most challenging, and rarely directly addressed, task in speech synthesis, especially for highly expressive data. Daft-Exprt uses FiLM conditioning layers to strategically inject different prosodic information in all parts of the architecture. The model explicitly encodes traditional low-level prosody features such as pitch, loudness and duration, but also higher level prosodic information that helps generating convincing voices in highly expressive styles. Speaker identity and prosodic information are disentangled through an adversarial training strategy that enables accurate prosody transfer across speakers. Experimental results show that Daft-Exprt significantly outperforms strong baselines on inter-text cross-speaker prosody transfer tasks, while yielding naturalness comparable to state-of-the-art expressive models. Moreover, results indicate that the model discards speaker identity information from the prosody representation, and consistently generate speech with the desired voice. We publicly release our code and provide speech samples from our experiments.