Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Evaluating Generalization and Robustness in Russian Anti-Spoofing: The RuASD Initiative

Ksenia Lysikova, Kirill Borodin, Kirill Borodin

Abstract

RuASD (Russian AntiSpoofing Dataset) is a dedicated, reproducible benchmark for Russian-language speech anti-spoofing designed to evaluate both in-domain discrimination and robustness to deployment-style distribution shifts. It combines a large spoof subset synthesized using 37 modern Russian-capable TTS and voice-cloning systems with a bona fide subset curated from multiple heterogeneous open Russian speech corpora, enabling systematic evaluation across diverse data sources. To emulate typical dissemination and channel effects in a controlled and reproducible manner, RuASD includes configurable simulations of platform and transmission distortions, including room reverberation, additive noise/music, and a range of speech-codec transcodings implemented via a unified processing chain. We benchmark a diverse set of publicly available anti-spoofing countermeasures spanning lightweight supervised architectures, graph-attention models, SSL-based detectors, and large-scale pretrained systems, and report reference results on both clean and simulated conditions to characterize robustness under realistic perturbation pipelines. The dataset is publickly available at \href{https://huggingface.co/datasets/MTUCI/RuASD}{\underline{Hugging Face}} and \href{https://modelscope.cn/datasets/lab260/RuASD}{\underline{ModelScope}}.

Evaluating Generalization and Robustness in Russian Anti-Spoofing: The RuASD Initiative

Abstract

RuASD (Russian AntiSpoofing Dataset) is a dedicated, reproducible benchmark for Russian-language speech anti-spoofing designed to evaluate both in-domain discrimination and robustness to deployment-style distribution shifts. It combines a large spoof subset synthesized using 37 modern Russian-capable TTS and voice-cloning systems with a bona fide subset curated from multiple heterogeneous open Russian speech corpora, enabling systematic evaluation across diverse data sources. To emulate typical dissemination and channel effects in a controlled and reproducible manner, RuASD includes configurable simulations of platform and transmission distortions, including room reverberation, additive noise/music, and a range of speech-codec transcodings implemented via a unified processing chain. We benchmark a diverse set of publicly available anti-spoofing countermeasures spanning lightweight supervised architectures, graph-attention models, SSL-based detectors, and large-scale pretrained systems, and report reference results on both clean and simulated conditions to characterize robustness under realistic perturbation pipelines. The dataset is publickly available at \href{https://huggingface.co/datasets/MTUCI/RuASD}{\underline{Hugging Face}} and \href{https://modelscope.cn/datasets/lab260/RuASD}{\underline{ModelScope}}.

Paper Structure

This paper contains 35 sections, 1 figure, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Speech Anti-Spoofing Datasets and Benchmarks
  4. Anti-Spoofing Architectures and Methods
  5. Dataset Construction
  6. TTS models
  7. Spoof generation protocol
  8. Data storage format.
  9. Objective spoof characterization.
  10. Bona fide sources
  11. Bona fide data selection protocol
  12. Candidate pool and selection.
  13. Objective bona fide characterization.
  14. Comparison of bona fide and spoof subsets.
  15. Data Augmentation
  16. ...and 20 more sections

Figures (1)

  • Figure 1: Objective descriptors for the bona fide subset across source corpora.