COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations

By Xavier Favory, Konstantinos Drossos, Tuomas Virtanen, Xavier Serra. 2020

35 citations recorded by the source corpus.

Audio representation learning based on deep neural networks (DNNs) emerged as an alternative approach to hand-crafted features. For achieving high performance, DNNs often need a large amount of annotated data which can be difficult and costly to obtain. In this paper, we propose a method for learning audio representations, aligning the learned latent representations of audio and associated tags. Aligning is done by maximizing the agreement of the latent representations of audio and tags, using a contrastive loss. The result is an audio embedding model which reflects acoustic and semantic characteristics of sounds. We evaluate the quality of our embedding model, measuring its performance as a feature extractor on three different tasks (namely, sound event recognition, and music genre and musical instrument classification), and investigate what type of characteristics the model captures. Our results are promising, sometimes in par with the state-of-the-art in the considered tasks and the embeddings produced with our method are well correlated with some acoustic descriptors.

Subfields: Music, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Music

In Signal Processing

Citations in the corpus

FSD50K: An Open Dataset of Human-Labeled Sound Events (2020, methodology): “, using the provided Freesound tags, title, and textual description for the clips) [91, 92]; evaluation of hierarchical classification via ontology-aware learning frameworks [5, 93, 94]; or approaches specifically combining strong and weak labels [95].”
Contrastive Representation Learning: A Framework and Review (2020, background): “In the same spirit of learning representations from loosely aligned data,COALA [30] learns a shared embedding between audio and its tags, which aremore readily available than a corresponding audio-transcript.”