Search papers, labs, and topics across Lattice.
The paper introduces Cross-Modal Robustness Transfer (CMRT) to improve the robustness of End-to-End Speech Translation (E2E-ST) models against morphological variations. CMRT leverages adversarial training in the text modality to transfer robustness to the speech modality, eliminating the need for computationally expensive adversarial speech data generation. Experiments across four language pairs show that CMRT improves adversarial robustness by over 3 BLEU points compared to baseline E2E-ST models.
Train robust speech translation models without generating adversarial speech data: transfer adversarial robustness from text using Cross-Modal Robustness Transfer (CMRT) and gain +3 BLEU.
End-to-End Speech Translation (E2E-ST) has seen significant advancements, yet current models are primarily benchmarked on curated,"clean"datasets. This overlooks critical real-world challenges, such as morphological robustness to inflectional variations common in non-native or dialectal speech. In this work, we adapt a text-based adversarial attack targeting inflectional morphology to the speech domain and demonstrate that state-of-the-art E2E-ST models are highly vulnerable it. While adversarial training effectively mitigates such risks in text-based tasks, generating high-quality adversarial speech data remains computationally expensive and technically challenging. To address this, we propose Cross-Modal Robustness Transfer (CMRT), a framework that transfers adversarial robustness from the text modality to the speech modality. Our method eliminates the requirement for adversarial speech data during training. Extensive experiments across four language pairs demonstrate that CMRT improves adversarial robustness by an average of more than 3 BLEU points, establishing a new baseline for robust E2E-ST without the overhead of generating adversarial speech.
