A Human-Inspired Decoupled Architecture for Efficient Audio Representation Learning

Increasing depth of transformer models improves recognition, but it comes at a substantial cost. Each additional layer requires more parameters, which makes the process computationally inefficient. We ask whether additional processing can focus on integrating features already computed. Looped Audio Spectrogram Transformer (LAST) first processes all tokens, then reuses the same blocks to refine only the class token over fixed audio features, thereby making later passes inexpensive. On AudioSet, ten-pass LAST achieves 0.345 mean average precision, exceeding a twelve-layer sequential transformer by 2.1% relative with 49.4% fewer parameters, 42% fewer multiply-accumulate operations, and 9.8% higher measured throughput. Across separately trained models, increasing the pass count from two to ten improves accuracy while adding only 1.2% computation. Further evaluations show improved robustness to temporal masking and various other auditory augmentations, with better generalization on classification tasks with music, environmental, and event sounds.

General audio foundation models have recently achieved remarkable progress, enabling strong performance across diverse tasks. However, state-of-the-art models remain extremely large, often with hundreds of millions of parameters, leading to high inference costs and limited deployability on edge devices. Knowledge distillation is a proven strategy for model compression, but prior work in audio has mostly focused on supervised settings, relying on class logits, intermediate features, or architecture-specific techniques. Such assumptions exclude models that output only embeddings, such as self-supervised or metric-learning models. We introduce S-SONDO (Self-Supervised KnOwledge DistillatioN for General AuDio FOundation Models), the first framework to distill general audio models using only their output embeddings. By avoiding the need for logits or layer-level alignment, S-SONDO is architecture-agnostic and broadly applicable to embedding-based teachers. We demonstrate its effectiveness by distilling two audio foundation models into three efficient students that are up to 61 times smaller while retaining up to 96% of teacher performance. We also provide practical insights on loss choice and clustering-based balanced data sampling. Code is available here: https://github.com/MedAliAdlouni/ssondo.

Self-supervised learning (SSL) has driven substantial progress in audio representation learning, though existing methods have increasingly relied on elaborate pre-training recipes to reach competitive performance. A markedly different pre-training philosophy underpins the most influential progress in language modeling and, more recently, in visual representation learning: rather than train encoders as static feature extractors, models are trained to predict the next element, a discrete token or a continuous embedding, from the preceding context. Autoregressive prediction thereby provides a unified pre-training interface that transfers across modalities, compelling the model to learn the underlying data distribution. We ask whether such a simple causal paradigm can yield strong audio learners, given that audio's temporal structure makes autoregressive prediction of patch embeddings a natural fit. We introduce NAPE (Next-Audio-Patch-Embedding prediction), a self-supervised framework in which a causal Transformer predicts each next patch embedding of a log-mel spectrogram from the previous ones, using causal masking and stop-gradient as its sole training signal. The design is intentionally minimalist, avoiding reconstruction decoders, acoustic tokenizers, student-teacher setups, and auxiliary regularization losses. Across six audio and speech benchmarks, NAPE achieves state-of-the-art fine-tuning performance on several tasks, scales consistently across encoder sizes, and yields strong linear-probing results. NAPE also produces structured attention patterns without explicit supervision.