EnvGAN: a GAN-based augmentation to improve environmental sound classification

Madhu, Aswathy; Kumar, Suresh

doi:10.1007/s10462-022-10153-0

Cited by 13 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned earlier, although existing GAN models have shown the potential of sound data augmentation [ 19 ], their effectiveness is quite limited in multi-class applications such as ASC. To overcome this, we propose DualDiscWaveGAN, a new GAN model for conditional animal sound generation.…”

Section: Methodsmentioning

confidence: 99%

“…They showed that the accuracy of two classifiers trained with augmented data by WCCGAN improved significantly on four environmental sound datasets. Madhu and Suresh [ 19 ] developed an unconditional GAN-based augmentation model by adding two layers and one stable loss function to WaveGAN [ 20 ] to generate longer virtual waveforms suitable for representing environmental sounds. However, this approach requires a class-specific generative model to generate class-specific data properly in a multi-class environment.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

DualDiscWaveGAN-Based Data Augmentation Scheme for Animal Sound Classification

Kim

Moon

Shim

et al. 2023

Sensors

View full text Add to dashboard Cite

Animal sound classification (ASC) refers to the automatic identification of animal categories by sound, and is useful for monitoring rare or elusive wildlife. Thus far, deep-learning-based models have shown good performance in ASC when training data is sufficient, but suffer from severe performance degradation if not. Recently, generative adversarial networks (GANs) have shown the potential to solve this problem by generating virtual data. However, in a multi-class environment, existing GAN-based methods need to construct separate generative models for each class. Additionally, they only consider the waveform or spectrogram of sound, resulting in poor quality of the generated sound. To overcome these shortcomings, we propose a two-step sound augmentation scheme using a class-conditional GAN. First, common features are learned from all classes of animal sounds, and multiple classes of animal sounds are generated based on the features that consider both waveforms and spectrograms using class-conditional GAN. Second, we select data from the generated data based on the confidence of the pretrained ASC model to improve classification performance. Through experiments, we show that the proposed method improves the accuracy of the basic ASC model by up to 18.3%, which corresponds to a performance improvement of 13.4% compared to the second-best augmentation method.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

DualDiscWaveGAN-Based Data Augmentation Scheme for Animal Sound Classification

Kim

Moon

Shim

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…There are plenty of works that address the problem of low data regimes [39]- [45]. However, their datasets and model architectures differ from those used in this work.…”

Section: B Computer Vision Vs Cybersecurity Low Data Regimesmentioning

confidence: 99%

Evasion Generative Adversarial Network for Low Data Regimes

Randhawa

Aslam

Alauthman

et al. 2023

IEEE Trans. Artif. Intell.

View full text Add to dashboard Cite

A myriad of recent literary works has leveraged generative adversarial networks (GANs) to generate unseen evasion samples. The purpose is to annex the generated data with the original train set for adversarial training to improve the detection performance of machine learning (ML) classifiers. The quality of generated adversarial samples relies on the adequacy of training data samples. However, in low data regimes like medical diagnostic imaging and cybersecurity, the anomaly samples are scarce in number. This paper proposes a novel GAN design called Evasion Generative Adversarial Network (EVAGAN) that is more suitable for low data regime problems that use oversampling for detection improvement of ML classifiers. EVAGAN not only can generate evasion samples, but its discriminator can act as an evasion-aware classifier. We have considered Auxiliary Classifier GAN (ACGAN) as a benchmark to evaluate the performance of EVAGAN on cybersecurity (ISCX-2014, CIC-2017 and CIC2018) botnet and computer vision (MNIST) datasets. We demonstrate that EVAGAN outperforms ACGAN for unbalanced datasets with respect to detection performance, training stability and time complexity. EVAGAN's generator quickly learns to generate the low sample class and hardens its discriminator simultaneously. In contrast to ML classifiers that require security hardening after being adversarially trained by GAN-generated data, EVAGAN renders it needless. The experimental analysis proves that EVA-GAN is an efficient evasion hardened model for low data regimes for the selected cybersecurity and computer vision datasets. Code will be available at HTTPS://www.github.com/rhr407/EVAGAN. Impact Statement-Artificial Intelligence (AI) applications can help improve the quality of human life. The use of AI is not only limited to medical anomaly detection and drug discovery but can be leveraged in computer networks to keep people safe from malicious activities on the Internet. However, the AI-based models can be biased towards the majority class of data on which they are trained due to data imbalance. Anomaly data samples are always scarce as compared to normal data samples. So this is an open research problem to solve. Our work is an effort to improve the AI-based methods in detection performance, stability and time complexity. Using the proposed technique, we can train our AI model using fewer anomaly samples, improving the costefficiency compared to state-of-the-art in anomaly detection.

show abstract

“…In image processing, GANs are widely used for generating and restoring images of faces, scenes, and Renaissance styles [10,11]. In the field of speech, GANs are utilized for generating high-quality speech samples and speech recognition [12,13]. In natural language processing, GANs are employed to generate text content with good semantics [14,15].…”

Section: Introductionmentioning

confidence: 99%

Data Generation with GAN Networks for Sidescan Sonar in Semantic Segmentation Applications

Yang,

Wang,

Cheng

et al. 2023

JMSE

View full text Add to dashboard Cite

In the realm of underwater exploration, particularly within the domain of autonomous detection, sidescan sonar stands as a pivotal sensor apparatus. Autonomous detection models necessitate a substantial volume of scanned sonar image data for optimal training, yet the challenges and costs associated with acquiring such data pose significant limitations on the deployment of autonomous detection models in underwater exploration scenarios. Consequently, there arises a demand for the development of cost-effective data augmentation techniques. In the present investigation, an initial collection of scanned sonar image data was conducted during lake trials, encompassing diverse environmental regions, including rocky terrain, shadowed areas, and aquatic bodies. Subsequently, a proprietary generative adversarial network (GAN) model was devised for the purpose of synthesizing scanned sonar data. The synthesized data underwent denoising and underwent post-processing via algorithmic methods. Subsequently, similarity metrics were computed to gauge the quality of the generated scanned sonar data. Furthermore, a semantic segmentation model was meticulously crafted and trained by employing authentic data. The generated data were subsequently introduced into this semantic segmentation model. The output outcomes demonstrated that the model exhibited preliminary labeling proficiency on the generated image data, requiring only minimal manual intervention to conform to the standards of a conventional dataset. Following the inclusion of the labeled data into the original dataset and the subsequent training of the network model utilizing the expanded dataset, there was an observed discernible enhancement in the segmentation performance of the model.

show abstract

EnvGAN: a GAN-based augmentation to improve environmental sound classification

Cited by 13 publications

References 46 publications

DualDiscWaveGAN-Based Data Augmentation Scheme for Animal Sound Classification

DualDiscWaveGAN-Based Data Augmentation Scheme for Animal Sound Classification

Evasion Generative Adversarial Network for Low Data Regimes

Data Generation with GAN Networks for Sidescan Sonar in Semantic Segmentation Applications

Contact Info

Product

Resources

About