SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification

03/31/2021
by   Helin Wang, et al.
0

In this paper, we present SpecAugment++, a novel data augmentation method for deep neural networks based acoustic scene classification (ASC). Different from other popular data augmentation methods such as SpecAugment and mixup that only work on the input space, SpecAugment++ is applied to both the input space and the hidden space of the deep neural networks to enhance the input and the intermediate feature representations. For an intermediate hidden state, the augmentation techniques consist of masking blocks of frequency channels and masking blocks of time frames, which improve generalization by enabling a model to attend not only to the most discriminative parts of the feature, but also the entire parts. Apart from using zeros for masking, we also examine two approaches for masking based on the use of other samples within the minibatch, which helps introduce noises to the networks to make them more discriminative for classification. The experimental results on the DCASE 2018 Task1 dataset and DCASE 2019 Task1 dataset show that our proposed method can obtain 3.6 4.7 CP-ResNet) respectively, and outperforms other previous data augmentation methods.

READ FULL TEXT
research
09/12/2021

Good-Enough Example Extrapolation

This paper asks whether extrapolating the hidden space distribution of t...
research
10/23/2019

Deja-vu: Double Feature Presentation in Deep Transformer Networks

Deep acoustic models typically receive features in the first layer of th...
research
05/27/2020

ACGAN-based Data Augmentation Integrated with Long-term Scalogram for Acoustic Scene Classification

In acoustic scene classification (ASC), acoustic features play a crucial...
research
01/10/2023

Look Beyond Bias with Entropic Adversarial Data Augmentation

Deep neural networks do not discriminate between spurious and causal pat...
research
02/12/2020

Efficient Training of Deep Convolutional Neural Networks by Augmentation in Embedding Space

Recent advances in the field of artificial intelligence have been made p...
research
12/17/2020

Joint Search of Data Augmentation Policies and Network Architectures

The common pipeline of training deep neural networks consists of several...
research
05/05/2021

Acoustic Scene Classification Using Multichannel Observation with Partially Missing Channels

Sounds recorded with smartphones or IoT devices often have partially unr...

Please sign up or login with your details

Forgot password? Click here to reset