PEFT for Speech: Unveiling Optimal Placement, Merging Strategies, and Ensemble Techniques
Part Of
2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 - Proceedings
Start Page
705
End Page
709
ISBN (of the container)
979-835037451-3
Date Issued
2024-04-14
Author(s)
Abstract
Parameter-Efficient Fine-Tuning (PEFT) is increasingly recognized as an effective method in speech processing. However, the optimal approach and the placement of PEFT methods remain inconclusive. Our study conducts extensive experiments to compare different PEFT methods and their layer-wise placement adapting Differentiable Architecture Search (DARTS). We also explore the use of ensemble learning to leverage diverse PEFT strategies. The results reveal that DARTS does not outperform the baseline approach, which involves inserting the same PEFT method into all layers of a Self-Supervised Learning (SSL) model. In contrast, an ensemble learning approach, particularly one employing majority voting, demonstrates superior performance. Our statistical evidence indicates that different PEFT methods learn in varied ways. This variation might explain why the synergistic integration of various PEFT methods through ensemble learning can harness their unique learning capabilities more effectively compared to individual layer-wise optimization.
Event(s)
49th IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024
Publisher
IEEE
Type
conference paper