# CoDiff-VC: A Codec-Assisted Diffusion Model for Zero-shot Voice Conversion

arXiv: https://arxiv.org/abs/2411.18918 · HTML: https://mlsanity.com/paper/2411.18918/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 28 Nov 2024.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [WaveGrad: Estimating Gradients for Waveform Generation](https://mlsanity.com/paper/2009.00713/) (2020)
- [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](https://mlsanity.com/paper/2112.02418/) (2021)
- [NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers](https://mlsanity.com/paper/2304.09116/) (2023)
- [AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss](https://mlsanity.com/paper/1905.05879/) (2019)
- [WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2102.01547/) (2021)
- [An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning](https://mlsanity.com/paper/2008.03648/) (2020)
- [Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme](https://mlsanity.com/paper/2109.13821/) (2021)
- [Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation](https://mlsanity.com/paper/2106.03153/) (2021)
- [Better speech synthesis through scaling](https://mlsanity.com/paper/2305.07243/) (2023)
- [DiffSVC: A Diffusion Probabilistic Model for Singing Voice Conversion](https://mlsanity.com/paper/2105.13871/) (2021)
- [Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models](https://mlsanity.com/paper/2211.09383/) (2022)
- [Fewer-token Neural Speech Codec with Time-invariant Codes](https://mlsanity.com/paper/2310.00014/) (2023)
- [SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention](https://mlsanity.com/paper/2312.08676/) (2023)
- [LM-VC: Zero-shot Voice Conversion via Speech Generation based on Language Models](https://mlsanity.com/paper/2306.10521/) (2023)
- [Content-Dependent Fine-Grained Speaker Embedding for Zero-Shot Speaker Adaptation in Text-to-Speech Synthesis](https://mlsanity.com/paper/2204.00990/) (2022)
- [Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features](https://mlsanity.com/paper/2112.04424/) (2021)
- [SIG-VC: A Speaker Information Guided Zero-shot Voice Conversion System for Both Human Beings and Machines](https://mlsanity.com/paper/2111.03811/) (2021)
- [Preserving background sound in noise-robust voice conversion via multi-task learning](https://mlsanity.com/paper/2211.03036/) (2022)

## Abstract (arXiv)

Zero-shot voice conversion (VC) aims to convert the original speaker's timbre to any target speaker while keeping the linguistic content. Current mainstream zero-shot voice conversion approaches depend on pre-trained recognition models to disentangle linguistic content and speaker representation. This results in a timbre residue within the decoupled linguistic content and inadequacies in speaker representation modeling. In this study, we propose CoDiff-VC, an end-to-end framework for zero-shot voice conversion that integrates a speech codec and a diffusion model to produce high-fidelity waveforms. Our approach involves employing a single-codebook codec to separate linguistic content from the source speech. To enhance content disentanglement, we introduce Mix-Style layer normalization (MSLN) to perturb the original timbre. Additionally, we incorporate a multi-scale speaker timbre modeling approach to ensure timbre consistency and improve voice detail similarity. To improve speech quality and speaker similarity, we introduce dual classifier-free guidance, providing both content and timbre guidance during the generation process. Objective and subjective experiments affirm that CoDiff-VC significantly improves speaker similarity, generating natural and higher-quality speech.