Pūkeko use sound elements to create calls and combine them to create complex call sequences in order to expand the range of ...

On first launch, you'll see a welcome screen where you can choose how intense you want your experience to be. Don't worry - you can always change settings later!

Abstract: In this study, we explore the use of Vector Quantized Variational Autoencoders (VQ-VAE) for real-time audio spectrogram inpainting, with a focus on minimizing environmental impact. We ...

The ESC-50 dataset is a labeled collection of 2000 environmental audio recordings suitable for benchmarking methods of environmental sound classification. The dataset consists of 5-second-long ...

Abstract: While DCGAN as deep learning model utilizing spectrogram, allows for detection of deepfake audio, it is prone to overfitting which affects its ability to discriminate between real and fake ...