Unsupervised Representation Learning For Context of Vocal Music

by   Camille Noufi, et al.

In this paper we aim to learn meaningful representations of sung intonation patterns derived from surrounding data without supervision. We focus on two facets of context in which a vocal line is produced: 1) within the short-time context of contiguous vocalizations, and 2) within the larger context of a recording. We propose two unsupervised deep learning methods, pseudo-task learning and slot filling, to produce latent encodings of these con-textual representations. To evaluate the quality of these representations and their usefulness as meaningful feature space, we conduct classification tasks on recordings sung by both professional and amateur singers. Initial results indicate that the learned representations enhance the performance of downstream classification tasks by several points, as compared to learning directly from the intonation contours alone. Larger increases in performance on classification of technique and vocal phrase patterns suggest that the representations encode short-time temporal context learned directly from the original recordings. Additionally, their ability to improve singer and gender identification suggest the learning of more broad contextual pat-terns. The growing availability of large unlabeled datasets makes this idea of contextual representation learning additionally promising, with larger amounts of meaningful samples often yielding better performance


page 1

page 2

page 3

page 4


Multi-Task Unsupervised Contextual Learning for Behavioral Annotation

Unsupervised learning has been an attractive method for easily deriving ...

A Theoretical Analysis of Contrastive Unsupervised Representation Learning

Recent empirical works have successfully used unlabeled data to learn fe...

PatchVAE: Learning Local Latent Codes for Recognition

Unsupervised representation learning holds the promise of exploiting lar...

Tile2Vec: Unsupervised representation learning for remote sensing data

Remote sensing lacks methods like the word vector representations and pr...

INFODENS: An Open-source Framework for Learning Text Representations

The advent of representation learning methods enabled large performance ...

Deep Representation Learning with Part Loss for Person Re-Identification

Learning discriminative representations for unseen person images is crit...