Exploring Efficient-tuning Methods in Self-supervised Speech Models

Understand

In this study, we aim to explore efficient tuning methods for speech self-supervised learning.

• Recent studies show that self-supervised learning (SSL) can learn powerful representations for different speech tasks.
• However, fine-tuning pre-trained models for each downstream task is parameter-inefficient since SSL models are notoriously large with millions of parameters.
• Adapters are lightweight modules commonly used in NLP to solve this problem.