Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofing
This addresses performance declines in anti-spoofing for multilingual and low-resource language scenarios, though it is incremental as it builds on existing monolingual models.
The paper tackled the problem of language mismatch degrading performance in cross-lingual speech anti-spoofing systems, and by proposing an accent-based data expansion method, it reduced these effects by over 15% on a dataset of over 3 million samples across 12 languages.
The effects of language mismatch impact speech anti-spoofing systems, while investigations and quantification of these effects remain limited. Existing anti-spoofing datasets are mainly in English, and the high cost of acquiring multilingual datasets hinders training language-independent models. We initiate this work by evaluating top-performing speech anti-spoofing systems that are trained on English data but tested on other languages, observing notable performance declines. We propose an innovative approach - Accent-based data expansion via TTS (ACCENT), which introduces diverse linguistic knowledge to monolingual-trained models, improving their cross-lingual capabilities. We conduct experiments on a large-scale dataset consisting of over 3 million samples, including 1.8 million training samples and nearly 1.2 million testing samples across 12 languages. The language mismatch effects are preliminarily quantified and remarkably reduced over 15% by applying the proposed ACCENT. This easily implementable method shows promise for multilingual and low-resource language scenarios.