ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks

TL;DR

This paper introduces ELP-adapter tuning, a parameter-efficient method for adapting speech processing models to various tasks, achieving comparable or better performance than full fine-tuning with significantly fewer parameters.

Contribution

The paper proposes a novel adapter-based fine-tuning approach with three types of adapters, enabling efficient multi-task speech model adaptation with minimal parameter updates.

Findings

Achieves comparable or superior performance to full fine-tuning.

Reduces the number of learnable parameters by 90%.

Effective across multiple speech processing tasks.

Abstract

Self-supervised learning has emerged as a key approach for learning generic representations from speech data. Despite promising results in downstream tasks such as speech recognition, speaker verification, and emotion recognition, a significant number of parameters is required, which makes fine-tuning for each task memory-inefficient. To address this limitation, we introduce ELP-adapter tuning, a novel method for parameter-efficient fine-tuning using three types of adapter, namely encoder adapters (E-adapters), layer adapters (L-adapters), and a prompt adapter (P-adapter). The E-adapters are integrated into transformer-based encoder layers and help to learn fine-grained speech representations that are effective for speech recognition. The L-adapters create paths from each encoder layer to the downstream head and help to extract non-linguistic features from lower encoder layers that are effective for speaker verification and emotion recognition. The P-adapter appends pseudo features to CNN features to further improve effectiveness and efficiency. With these adapters, models can be quickly adapted to various speech processing tasks. Our evaluation across four downstream tasks using five backbone models demonstrated the effectiveness of the proposed method. With the WavLM backbone, its performance was comparable to or better than that of full fine-tuning on all tasks while requiring 90% fewer learnable parameters.