Representation Learning for the Automatic Indexing of Sound Effects Libraries

TL;DR

This paper proposes a dataset-independent, taxonomy-agnostic representation learning method for sound effects libraries, improving search and categorization despite inconsistent metadata and limited data, outperforming existing methods like OpenL3.

Contribution

It introduces a novel, generalized embedding approach for sound effects that overcomes dataset limitations and taxonomy issues, enhancing sound library management.

Findings

Dataset-independent embeddings outperform OpenL3

Metric learning improves representation quality

Cross-dataset training enhances generalization

Abstract

Labeling and maintaining a commercial sound effects library is a time-consuming task exacerbated by databases that continually grow in size and undergo taxonomy updates. Moreover, sound search and taxonomy creation are complicated by non-uniform metadata, an unrelenting problem even with the introduction of a new industry standard, the Universal Category System. To address these problems and overcome dataset-dependent limitations that inhibit the successful training of deep learning models, we pursue representation learning to train generalized embeddings that can be used for a wide variety of sound effects libraries and are a taxonomy-agnostic representation of sound. We show that a task-specific but dataset-independent representation can successfully address data issues such as class imbalance, inconsistent class labels, and insufficient dataset size, outperforming established representations such as OpenL3. Detailed experimental results show the impact of metric learning approaches and different cross-dataset training methods on representational effectiveness.