# Discrete Optimal Transport and Voice Conversion

arXiv: https://arxiv.org/abs/2505.04382 · HTML: https://mlsanity.com/paper/2505.04382/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 7 May 2025.

## Builds on (most cited first, 17 of 17)

- [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)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Multisample Flow Matching: Straightening Flows with Minibatch Couplings](https://mlsanity.com/paper/2304.14772/) (2023)
- [AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks](https://mlsanity.com/paper/2110.01200/) (2021)
- [Neural Optimal Transport](https://mlsanity.com/paper/2201.12220/) (2022)
- [Adapting Frechet Audio Distance for Generative Music Evaluation](https://mlsanity.com/paper/2311.01616/) (2023)
- [The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech](https://mlsanity.com/paper/2409.09305/) (2024)
- [Voice Conversion With Just Nearest Neighbors](https://mlsanity.com/paper/2305.18975/) (2023)
- [ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech](https://mlsanity.com/paper/2502.08857/) (2025)
- [Whisper: Fast Flooding for Low-Power Wireless Networks](https://mlsanity.com/paper/1809.03699/) (2018)
- [Improving Short Utterance Anti-Spoofing with AASIST2](https://mlsanity.com/paper/2309.08279/) (2023)
- [AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge](https://mlsanity.com/paper/2408.17352/) (2024)
- [ControlVC: Zero-Shot Voice Conversion with Time-Varying Controls on Pitch and Speed](https://mlsanity.com/paper/2209.11866/) (2022)
- [Optimal Transport Maps are Good Voice Converters](https://mlsanity.com/paper/2411.02402/) (2024)

## Built on by (most cited first, 1 of 1)

- [Discrete optimal transport is a strong audio adversarial attack](https://mlsanity.com/paper/2509.14959/) (2025)

## Abstract (arXiv)

We propose kDOT, a discrete optimal transport (OT) framework for voice conversion (VC) operating in a pretrained speech embedding space. In contrast to the averaging strategies used in kNN-VC and SinkVC, and the independence assumption adopted in MKL, our method employs the barycentric projection of the discrete OT plan to construct a transport map between source and target speaker embedding distributions. We conduct a comprehensive ablation study over the number of transported embeddings and systematically analyze the impact of source and target utterance duration. Experiments on LibriSpeech demonstrate that OT with barycentric projection consistently improves distribution alignment and often outperforms averaging-based approaches in terms of WER, MOS, and FAD. Furthermore, we show that applying discrete OT as a post-processing step can transform spoofed speech into samples that are misclassified as bona fide by a state-of-the-art spoofing detector. This demonstrates the strong domain adaptation capability of OT in embedding space, while also revealing important security implications for spoof detection systems.