PALM: Few-Shot Prompt Learning for Audio Language Models

TL;DR

PALM introduces a novel prompt learning method for Audio-Language Models that optimizes text encoder features, improving efficiency and performance in few-shot audio recognition tasks across multiple datasets.

Contribution

The paper proposes PALM, a new prompt learning approach that enhances ALMs by optimizing text encoder features, leading to better efficiency and comparable or superior results.

Findings

PALM outperforms baseline methods in few-shot audio recognition.

The approach is computationally more efficient than existing methods.

Effective across diverse speech-processing datasets.

Abstract

Audio-Language Models (ALMs) have recently achieved remarkable success in zero-shot audio recognition tasks, which match features of audio waveforms with class-specific text prompt features, inspired by advancements in Vision-Language Models (VLMs). Given the sensitivity of zero-shot performance to the choice of hand-crafted text prompts, many prompt learning techniques have been developed for VLMs. We explore the efficacy of these approaches in ALMs and propose a novel method, Prompt Learning in Audio Language Models (PALM), which optimizes the feature space of the text encoder branch. Unlike existing methods that work in the input space, our approach results in greater training efficiency. We demonstrate the effectiveness of our approach on 11 audio recognition datasets, encompassing a variety of speech-processing tasks, and compare the results with three baselines in a few-shot learning setup. Our method is either on par with or outperforms other approaches while being computationally less demanding. Code is available at https://asif-hanif.github.io/palm/