Pith. sign in

REVIEW

Enhancing Audio Augmentation Methods with Consistency Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2102.05151 v3 pith:URTFG77Z submitted 2021-02-09 cs.SD cs.LGeess.AS

Enhancing Audio Augmentation Methods with Consistency Learning

classification cs.SD cs.LGeess.AS
keywords classificationconsistencydataaudioaugmentationlearninglosscross-entropy
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Data augmentation is an inexpensive way to increase training data diversity and is commonly achieved via transformations of existing data. For tasks such as classification, there is a good case for learning representations of the data that are invariant to such transformations, yet this is not explicitly enforced by classification losses such as the cross-entropy loss. This paper investigates the use of training objectives that explicitly impose this consistency constraint and how it can impact downstream audio classification tasks. In the context of deep convolutional neural networks in the supervised setting, we show empirically that certain measures of consistency are not implicitly captured by the cross-entropy loss and that incorporating such measures into the loss function can improve the performance of audio classification systems. Put another way, we demonstrate how existing augmentation methods can further improve learning by enforcing consistency.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.