An Investigation of Reprogramming for Cross-Language Adaptation in Speaker Verification Systems

TL;DR

This paper explores how adversarial reprogramming can enhance cross-language speaker verification, revealing that model capacity influences performance more than padding size, with larger models better maintaining accuracy.

Contribution

It investigates the relationship between padded parameter size and model performance, showing that larger models are more robust to reprogramming in cross-language SV tasks.

Findings

Reprogramming improves cross-language SV performance.

Larger models tolerate longer padding without degradation.

Performance is mainly influenced by model capacity, not padding size.

Abstract

Language mismatch is among the most common and challenging domain mismatches in deploying speaker verification (SV) systems. Adversarial reprogramming has shown promising results in cross-language adaptation for SV. The reprogramming is implemented by padding learnable parameters on the two sides of input speech signals. In this paper, we investigate the relationship between the number of padded parameters and the performance of the reprogrammed models. Sufficient experiments are conducted with different scales of SV models and datasets. The results demonstrate that reprogramming consistently improves the performance of cross-language SV, while the improvement is saturated or even degraded when using larger padding lengths. The performance is mainly determined by the capacity of the original SV models instead of the number of padded parameters. The SV models with larger scales have higher upper bounds in performance and can endure longer padding without performance degradation.