# Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model

arXiv: https://arxiv.org/abs/2502.05471 · HTML: https://mlsanity.com/paper/2502.05471/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2025.

## Built on by (most cited first, 8 of 8)

- [Discl-VC: Disentangled Discrete Tokens and In-Context Learning for Controllable Zero-Shot Voice Conversion](https://mlsanity.com/paper/2505.24291/) (2025)
- [EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion](https://mlsanity.com/paper/2505.16691/) (2025)
- [Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching](https://mlsanity.com/paper/2506.01014/) (2025)
- [NE-PADD: Leveraging Named Entity Knowledge for Robust Partial Audio Deepfake Detection via Attention Aggregation](https://mlsanity.com/paper/2509.03829/) (2025)
- [Provable Speech Attributes Conversion via Latent Independence](https://mlsanity.com/paper/2510.05191/) (2025)
- [MeanVoiceFlow: One-step Nonparallel Voice Conversion with Mean Flows](https://mlsanity.com/paper/2602.18104/) (2026)
- [DiFlow-TTS: Compact and Low-Latency Zero-Shot Text-to-Speech with Discrete Flow Matching](https://mlsanity.com/paper/2509.09631/) (2025)
- [MeanVoiceFlow2: Joint Optimization of Mean Flow and Content Encoder for Fast One-Step Zero-Shot Voice Conversion](https://mlsanity.com/paper/2609.40087/) (2026)

## Abstract (arXiv)

This paper introduces PFlow-VC, a conditional flow matching voice conversion model that leverages fine-grained discrete pitch tokens and target speaker prompt information for expressive voice conversion (VC). Previous VC works primarily focus on speaker conversion, with further exploration needed in enhancing expressiveness (such as prosody and emotion) for timbre conversion. Unlike previous methods, we adopt a simple and efficient approach to enhance the style expressiveness of voice conversion models. Specifically, we pretrain a self-supervised pitch VQVAE model to discretize speaker-irrelevant pitch information and leverage a masked pitch-conditioned flow matching model for Mel-spectrogram synthesis, which provides in-context pitch modeling capabilities for the speaker conversion model, effectively improving the voice style transfer capacity. Additionally, we improve timbre similarity by combining global timbre embeddings with time-varying timbre tokens. Experiments on unseen LibriTTS test-clean and emotional speech dataset ESD show the superiority of the PFlow-VC model in both timbre conversion and style transfer. Audio samples are available on the demo page https://speechai-demo.github.io/PFlow-VC/.