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

Abstract

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.

8 pages, 1 figure, workshop on Self-supervision in Audio and Speech at the 37th International Conference on Machine Learning (ICML), 2020, Vienna, Austria

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Simple Framework for Contrastive Learning of Visual Representations
• How transferable are features in deep neural networks?
• Neural Discrete Representation Learning
• A guide to convolution arithmetic for deep learning
• YouTube-8M: A Large-Scale Video Classification Benchmark
• Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
• SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability
• Representation Learning of Music Using Artist Labels
• Data Augmentation for Instrument Classification Robust to Audio Effects

Cited by in corpus (5)

• Contrastive Representation Learning: A Framework and Review
• MusCaps: Generating Captions for Music Audio
• Enriched Music Representations with Multiple Cross-modal Contrastive Learning
• Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval
• Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning