# Text-free non-parallel many-to-many voice conversion using normalising flows

arXiv: https://arxiv.org/abs/2203.08009 · HTML: https://mlsanity.com/paper/2203.08009/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2022.

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

- [Enhancing the Stability of LLM-based Speech Generation Systems through Self-Supervised Representations](https://mlsanity.com/paper/2402.03407/) (2024)
- [Rethinking MUSHRA: Addressing Modern Challenges in Text-to-Speech Evaluation](https://mlsanity.com/paper/2411.12719/) (2024)
- [vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoders](https://mlsanity.com/paper/2409.01995/) (2024)
- [An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASR](https://mlsanity.com/paper/2503.08954/) (2025)
- [Computer-assisted Pronunciation Training -- Speech synthesis is almost all you need](https://mlsanity.com/paper/2207.00774/) (2022)
- [Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech](https://mlsanity.com/paper/2307.16679/) (2023)
- [AE-Flow: AutoEncoder Normalizing Flow](https://mlsanity.com/paper/2312.16552/) (2023)
- [Creating New Voices using Normalizing Flows](https://mlsanity.com/paper/2312.14569/) (2023)
- [DisC-VC: Disentangled and F0-Controllable Neural Voice Conversion](https://mlsanity.com/paper/2210.11059/) (2022)
- [Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-Speech](https://mlsanity.com/paper/2309.08255/) (2023)

## Abstract (arXiv)

Non-parallel voice conversion (VC) is typically achieved using lossy representations of the source speech. However, ensuring only speaker identity information is dropped whilst all other information from the source speech is retained is a large challenge. This is particularly challenging in the scenario where at inference-time we have no knowledge of the text being read, i.e., text-free VC. To mitigate this, we investigate information-preserving VC approaches. Normalising flows have gained attention for text-to-speech synthesis, however have been under-explored for VC. Flows utilize invertible functions to learn the likelihood of the data, thus provide a lossless encoding of speech. We investigate normalising flows for VC in both text-conditioned and text-free scenarios. Furthermore, for text-free VC we compare pre-trained and jointly-learnt priors. Flow-based VC evaluations show no degradation between text-free and text-conditioned VC, resulting in improvements over the state-of-the-art. Also, joint-training of the prior is found to negatively impact text-free VC quality.