Evaluating Generalization and Robustness in Russian Anti-Spoofing: The RuASD Initiative
This benchmark addresses the lack of standardized evaluation for Russian anti-spoofing, enabling systematic comparison of countermeasures under realistic distribution shifts.
RuASD provides a benchmark for Russian-language anti-spoofing, combining a large spoof subset from 37 TTS/voice-cloning systems with bona fide speech from multiple corpora, and includes configurable distortions to test robustness. Reference results show that SSL-based detectors achieve the best performance, with EER improvements of up to 30% over lightweight models under clean conditions.
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}}.