# DRVC: A Framework of Any-to-Any Voice Conversion with Self-Supervised Learning

arXiv: https://arxiv.org/abs/2202.10976 · HTML: https://mlsanity.com/paper/2202.10976/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2022.

## Built on by (most cited first, 9 of 9)

- [SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention](https://mlsanity.com/paper/2312.08676/) (2023)
- [Pre-Avatar: An Automatic Presentation Generation Framework Leveraging Talking Avatar](https://mlsanity.com/paper/2210.06877/) (2022)
- [Towards General-Purpose Text-Instruction-Guided Voice Conversion](https://mlsanity.com/paper/2309.14324/) (2023)
- [Reimagining Speech: A Scoping Review of Deep Learning-Powered Voice Conversion](https://mlsanity.com/paper/2311.08104/) (2023)
- [Semi-Supervised Learning Based on Reference Model for Low-resource TTS](https://mlsanity.com/paper/2210.14723/) (2022)
- [MetaSpeech: Speech Effects Switch Along with Environment for Metaverse](https://mlsanity.com/paper/2210.13811/) (2022)
- [Improving Imbalanced Text Classification with Dynamic Curriculum Learning](https://mlsanity.com/paper/2210.14724/) (2022)
- [Medical Speech Symptoms Classification via Disentangled Representation](https://mlsanity.com/paper/2403.05000/) (2024)
- [A survey of AI-generated voices and their detection](https://mlsanity.com/paper/2608.15411/) (2026)

## Abstract (arXiv)

Any-to-any voice conversion problem aims to convert voices for source and target speakers, which are out of the training data. Previous works wildly utilize the disentangle-based models. The disentangle-based model assumes the speech consists of content and speaker style information and aims to untangle them to change the style information for conversion. Previous works focus on reducing the dimension of speech to get the content information. But the size is hard to determine to lead to the untangle overlapping problem. We propose the Disentangled Representation Voice Conversion (DRVC) model to address the issue. DRVC model is an end-to-end self-supervised model consisting of the content encoder, timbre encoder, and generator. Instead of the previous work for reducing speech size to get content, we propose a cycle for restricting the disentanglement by the Cycle Reconstruct Loss and Same Loss. The experiments show there is an improvement for converted speech on quality and voice similarity.