# PAVITS: Exploring Prosody-aware VITS for End-to-End Emotional Voice Conversion

arXiv: https://arxiv.org/abs/2403.01494 · HTML: https://mlsanity.com/paper/2403.01494/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2024.

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

- [IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2506.21619/) (2025)
- [Vevo2: A Unified and Controllable Framework for Speech and Singing Voice Generation](https://mlsanity.com/paper/2508.16332/) (2025)
- [Unifying Speech Recognition, Synthesis and Conversion with Autoregressive Transformers](https://mlsanity.com/paper/2601.10770/) (2026)
- [Maestro-EVC: Controllable Emotional Voice Conversion Guided by References and Explicit Prosody](https://mlsanity.com/paper/2508.06890/) (2025)
- [Vibrato Expression Control for Singing Voice Conversion with Improving Independent Control](https://mlsanity.com/paper/2606.17126/) (2026)
- [Re-Sonance: A Dysarthric Asynchronous Real-Time Speech Conversion System Based on a Three-Stage Cascaded ASR-LLM-TTS Architecture](https://mlsanity.com/paper/2607.17615/) (2026)

## Abstract (arXiv)

In this paper, we propose Prosody-aware VITS (PAVITS) for emotional voice conversion (EVC), aiming to achieve two major objectives of EVC: high content naturalness and high emotional naturalness, which are crucial for meeting the demands of human perception. To improve the content naturalness of converted audio, we have developed an end-to-end EVC architecture inspired by the high audio quality of VITS. By seamlessly integrating an acoustic converter and vocoder, we effectively address the common issue of mismatch between emotional prosody training and run-time conversion that is prevalent in existing EVC models. To further enhance the emotional naturalness, we introduce an emotion descriptor to model the subtle prosody variations of different speech emotions. Additionally, we propose a prosody predictor, which predicts prosody features from text based on the provided emotion label. Notably, we introduce a prosody alignment loss to establish a connection between latent prosody features from two distinct modalities, ensuring effective training. Experimental results show that the performance of PAVITS is superior to the state-of-the-art EVC methods. Speech Samples are available at https://jeremychee4.github.io/pavits4EVC/ .