arXiv subjects

Anton Selitskiy

Publications and source records attributed to Anton Selitskiy.

4 recordsLinked to original sources

arXiv2026

Stability of the Monge Map in Semi-Dual Optimal Transport

This paper shows that the semi-dual formulation of the optimal transport problem has a degenerate saddle-point structure, and that its numerical solution is equivalent to solving a constrained optimization problem. We derive necessary and sufficient conditions for the convergence of Monge maps without requiring optimality of the dual potential. This analysis helps explain why, in practice, numerical algorithms often require more iterations to update the transport map than the potential.

math.OC↗

arXiv2026

Discrete Optimal Transport and Voice Conversion

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.

eess.AS↗

arXiv2026

Discrete optimal transport is a strong audio adversarial attack

In this paper, we investigate discrete optimal transport (DOT) as a black-box attack against modern automatic speaker verification (ASV) and anti-spoofing countermeasure (CM) systems. Our attack operates as a post-processing distribution-alignment step. Frame-level WavLM embeddings of generated speech (or another person speech) are aligned to an unpaired bona fide speech pool using entropic optimal transport and a top-k barycentric projection, followed by neural vocoding. Unlike gradient-based attacks, the proposed method requires no access to model parameters, gradients, or training data. Experiments on ASVspoof2019 and ASVspoof5 demonstrate that DOT attack substantially increases CM EER and substantially degrades ASV performance across multiple spoofing attacks. The attack transfers across datasets and remains effective after CM fine-tuning. Analysis using speaker similarity, Fréchet Audio Distance, and visualization of embedding distributions suggests that DOT succeeds by shifting source speech toward bona fide regions of the representation space rather than by maximizing speaker similarity. These results indicate that optimal-transport-based distribution alignment represents a previously underexplored attack vector for contemporary ASV and anti-spoofing systems.

eess.AS↗

arXiv2022

Music Source Separation with Generative Flow

Fully-supervised models for source separation are trained on parallel mixture-source data and are currently state-of-the-art. However, such parallel data is often difficult to obtain, and it is cumbersome to adapt trained models to mixtures with new sources. Source-only supervised models, in contrast, only require individual source data for training. In this paper, we first leverage flow-based generators to train individual music source priors and then use these models, along with likelihood-based objectives, to separate music mixtures. We show that in singing voice separation and music separation tasks, our proposed method is competitive with a fully-supervised approach. We also demonstrate that we can flexibly add new types of sources, whereas fully-supervised approaches would require retraining of the entire model.

eess.AS↗