Training neural audio classifiers with few data

10/24/2018
by   Jordi Pons, et al.
0

We investigate supervised learning strategies that improve the training of neural network audio classifiers on small annotated collections. In particular, we study whether (i) a naive regularization of the solution space, (ii) prototypical networks, (iii) transfer learning, or (iv) their combination, can foster deep learning models to better leverage a small amount of training examples. To this end, we evaluate (i-iv) for the tasks of acoustic event recognition and acoustic scene classification, considering from 1 to 100 labeled examples per class. Results indicate that transfer learning is a powerful strategy in such scenarios, but prototypical networks show promising results when one does not count with external or validation data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/27/2022

Uncertainty Calibration for Deep Audio Classifiers

Although deep Neural Networks (DNNs) have achieved tremendous success in...
research
09/02/2021

Transfer of Pretrained Model Weights Substantially Improves Semi-Supervised Image Classification

Deep neural networks produce state-of-the-art results when trained on a ...
research
06/21/2021

Do sound event representations generalize to other audio tasks? A case study in audio transfer learning

Transfer learning is critical for efficient information transfer across ...
research
06/14/2023

Iterative self-transfer learning: A general methodology for response time-history prediction based on small dataset

There are numerous advantages of deep neural network surrogate modeling ...
research
04/02/2021

On the Pitfalls of Learning with Limited Data: A Facial Expression Recognition Case Study

Deep learning models need large amounts of data for training. In video r...
research
11/15/2019

Cross-modal supervised learning for better acoustic representations

Obtaining large-scale human-labeled datasets to train acoustic represent...
research
11/10/2017

Deep Within-Class Covariance Analysis for Acoustic Scene Classification

Within-Class Covariance Normalization (WCCN) is a powerful post-processi...

Please sign up or login with your details

Forgot password? Click here to reset