SLAP: Scalable Language-Audio Pretraining with Variable-Duration Audio and Multi-Objective Training

TL;DR

SLAP introduces a scalable, multi-objective pretraining approach for language-audio models, handling large datasets and variable audio durations to improve dense audio representations and performance on retrieval and classification tasks.

Contribution

It presents a novel pretraining method that scales to 109 million pairs, integrates multiple training objectives, and supports variable-duration audio for enhanced audio representation learning.

Findings

Achieves state-of-the-art results on audio-text retrieval.

Improves zero-shot audio classification performance.

Handles variable-duration audio effectively.

Abstract

Contrastive language-audio pretraining (CLAP) has achieved notable success in learning semantically rich audio representations and is widely adopted for various audio-related tasks. However, current CLAP models face several key limitations. First, they are typically trained on relatively small datasets, often comprising a few million audio samples. Second, existing CLAP models are restricted to short and fixed duration, which constrains their usage in real-world scenarios with variable-duration audio. Third, the standard contrastive training objective operates on global representations, which may hinder the learning of dense, fine-grained audio features. To address these challenges, we introduce Scalable Language-Audio Pretraining (SLAP), which scales language-audio pretraining to 109 million audio-text pairs with variable audio durations and incorporates multiple training objectives. SLAP unifies contrastive loss with additional self-supervised and captioning losses in a single-stage training, facilitating the learning of richer dense audio representations. The proposed SLAP model achieves new state-of-the-art performance on audio-text retrieval and zero-shot audio classification tasks, demonstrating its effectiveness across diverse benchmarks.