# Towards Better Disentanglement in Non-Autoregressive Zero-Shot Expressive Voice Conversion

arXiv: https://arxiv.org/abs/2506.04013 · HTML: https://mlsanity.com/paper/2506.04013/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 30 of 30)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (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)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio](https://mlsanity.com/paper/2106.06909/) (2021)
- [emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation](https://mlsanity.com/paper/2312.15185/) (2023)
- [Seamless: Multilingual Expressive and Streaming Speech Translation](https://mlsanity.com/paper/2312.05187/) (2023)
- [Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset](https://mlsanity.com/paper/2010.14794/) (2020)
- [EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis](https://mlsanity.com/paper/2308.05725/) (2023)
- [FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion](https://mlsanity.com/paper/2210.15418/) (2022)
- [Voice Conversion With Just Nearest Neighbors](https://mlsanity.com/paper/2305.18975/) (2023)
- [mHuBERT-147: A Compact Multilingual HuBERT Model](https://mlsanity.com/paper/2406.06371/) (2024)
- [A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion](https://mlsanity.com/paper/2111.02392/) (2021)
- [Emotion Intensity and its Control for Emotional Voice Conversion](https://mlsanity.com/paper/2201.03967/) (2022)
- [HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis](https://mlsanity.com/paper/2311.12454/) (2023)
- [Textless Speech Emotion Conversion using Discrete and Decomposed Representations](https://mlsanity.com/paper/2111.07402/) (2021)
- [VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design](https://mlsanity.com/paper/2307.16430/) (2023)
- [Findings of the IWSLT 2024 Evaluation Campaign](https://mlsanity.com/paper/2411.05088/) (2024)
- [Face-Dubbing++: Lip-Synchronous, Voice Preserving Translation of Videos](https://mlsanity.com/paper/2206.04523/) (2022)
- [Nonparallel Emotional Speech Conversion](https://mlsanity.com/paper/1811.01174/) (2018)
- [Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training](https://mlsanity.com/paper/2103.16809/) (2021)
- [HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer](https://mlsanity.com/paper/2307.16171/) (2023)
- [Disentangling Prosody Representations with Unsupervised Speech Reconstruction](https://mlsanity.com/paper/2212.06972/) (2022)
- [EmoCat: Language-agnostic Emotional Voice Conversion](https://mlsanity.com/paper/2101.05695/) (2021)
- [Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features](https://mlsanity.com/paper/2211.04710/) (2022)
- [StyleS2ST: Zero-shot Style Transfer for Direct Speech-to-speech Translation](https://mlsanity.com/paper/2305.17732/) (2023)
- [Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversion](https://mlsanity.com/paper/2307.00393/) (2023)
- [Improving Pronunciation and Accent Conversion through Knowledge Distillation And Synthetic Ground-Truth from Native TTS](https://mlsanity.com/paper/2410.14997/) (2024)

## Built on by (most cited first, 2 of 2)

- [Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection](https://mlsanity.com/paper/2605.03039/) (2026)
- [KIT's Submission to Cross-Lingual Voice Cloning in IWSLT 2026](https://mlsanity.com/paper/2606.07240/) (2026)

## Abstract (arXiv)

Expressive voice conversion aims to transfer both speaker identity and expressive attributes from a target speech to a given source speech. In this work, we improve over a self-supervised, non-autoregressive framework with a conditional variational autoencoder, focusing on reducing source timbre leakage and improving linguistic-acoustic disentanglement for better style transfer. To minimize style leakage, we use multilingual discrete speech units for content representation and reinforce embeddings with augmentation-based similarity loss and mix-style layer normalization. To enhance expressivity transfer, we incorporate local F0 information via cross-attention and extract style embeddings enriched with global pitch and energy features. Experiments show our model outperforms baselines in emotion and speaker similarity, demonstrating superior style adaptation and reduced source style leakage.