CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models

TL;DR

This paper introduces CompA, benchmarks for evaluating compositional reasoning in audio-language models, and proposes CompA-CLAP, a fine-tuned model that significantly improves reasoning abilities on these benchmarks.

Contribution

The paper presents novel benchmarks for assessing compositional reasoning in ALMs and a new training method that enhances model performance on these tasks.

Findings

Current ALMs perform only marginally better than random chance on compositional reasoning.

CompA-CLAP significantly outperforms baseline models on the CompA benchmarks.

Proposed training improvements enable better understanding of acoustic event order and attributes.

Abstract

A fundamental characteristic of audio is its compositional nature. Audio-language models (ALMs) trained using a contrastive approach (e.g., CLAP) that learns a shared representation between audio and language modalities have improved performance in many downstream applications, including zero-shot audio classification, audio retrieval, etc. However, the ability of these models to effectively perform compositional reasoning remains largely unexplored and necessitates additional research. In this paper, we propose CompA, a collection of two expert-annotated benchmarks with a majority of real-world audio samples, to evaluate compositional reasoning in ALMs. Our proposed CompA-order evaluates how well an ALM understands the order or occurrence of acoustic events in audio, and CompA-attribute evaluates attribute-binding of acoustic events. An instance from either benchmark consists of two audio-caption pairs, where both audios have the same acoustic events but with different compositions. An ALM is evaluated on how well it matches the right audio to the right caption. Using this benchmark, we first show that current ALMs perform only marginally better than random chance, thereby struggling with compositional reasoning. Next, we propose CompA-CLAP, where we fine-tune CLAP using a novel learning method to improve its compositional reasoning abilities. To train CompA-CLAP, we first propose improvements to contrastive training with composition-aware hard negatives, allowing for more focused training. Next, we propose a novel modular contrastive loss that helps the model learn fine-grained compositional understanding and overcomes the acute scarcity of openly available compositional audios. CompA-CLAP significantly improves over all our baseline models on the CompA benchmark, indicating its superior compositional reasoning capabilities.