# Low-Complexity Audio Embedding Extractors

arXiv: https://arxiv.org/abs/2303.01879 · HTML: https://mlsanity.com/paper/2303.01879/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2023.

## Built on by (most cited first, 2 of 2)

- [Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models](https://mlsanity.com/paper/2310.15648/) (2023)
- [Neural Proxies for Sound Synthesizers: Learning Perceptually Informed Preset Representations](https://mlsanity.com/paper/2509.07635/) (2025)

## Abstract (arXiv)

Solving tasks such as speaker recognition, music classification, or semantic audio event tagging with deep learning models typically requires computationally demanding networks. General-purpose audio embeddings (GPAEs) are dense representations of audio signals that allow lightweight, shallow classifiers to tackle various audio tasks. The idea is that a single complex feature extractor would extract dense GPAEs, while shallow MLPs can produce task-specific predictions. If the extracted dense representations are general enough to allow the simple downstream classifiers to generalize to a variety of tasks in the audio domain, a single costly forward pass suffices to solve multiple tasks in parallel. In this work, we try to reduce the cost of GPAE extractors to make them suitable for resource-constrained devices. We use efficient MobileNets trained on AudioSet using Knowledge Distillation from a Transformer ensemble as efficient GPAE extractors. We explore how to obtain high-quality GPAEs from the model, study how model complexity relates to the quality of extracted GPAEs, and conclude that low-complexity models can generate competitive GPAEs, paving the way for analyzing audio streams on edge devices w.r.t. multiple audio classification and recognition tasks.