An Adapter-based Unified Model For Multiple Spoken Language Processing Tasks

Abstract

Self-supervised learning models have revolutionized the field of speech processing. However, the process of fine-tuning these models on downstream tasks requires substantial computational resources, particularly when dealing with multiple speech-processing tasks. In this paper, we explore the potential of adapter-based fine-tuning in developing a unified model capable of effectively handling multiple spoken language processing tasks. The tasks we investigate are Automatic Speech Recognition, Phoneme Recognition, Intent Classification, Slot Filling, and Spoken Emotion Recognition. We validate our approach through a series of experiments on the SUPERB benchmark, and our results indicate that adapter-based fine-tuning enables a single encoder-decoder model to perform multiple speech processing tasks with an average improvement of 18.4% across the five target tasks while staying efficient in terms of parameter updates.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysuresh2024an

Related papers

• Elp-adapters: Parameter Efficient Adapter Tuning For Various Speech Processing Tasks (2024)7.81
• Exploring Efficient-tuning Methods In Self-supervised Speech Models (2022)10.07
• Efficient Adapter Tuning Of Pre-trained Speech Models For Automatic Speaker Verification (2024)0.00
• Efficient Adapter Transfer Of Self-supervised Speech Models For Automatic Speech Recognition (2022)12.68
• Adapter-based Extension Of Multi-speaker Text-to-speech Model For New Speakers (2022)6.77
• How To Learn A New Language? An Efficient Solution For Self-supervised Learning Models Unseen Languages Adaption In Low-resource Scenario (2024)0.00
• Evaluating Parameter-efficient Transfer Learning Approaches On SURE Benchmark For Speech Understanding (2023)0.00
• ADAPTERMIX: Exploring The Efficacy Of Mixture Of Adapters For Low-resource TTS Adaptation (2023)6.34