A utility for wrapping the Free Spoken Digit Dataset into PyTorch-ready data set splits.

Speech Recognition on Spoken Digit Dataset using Bidirectional LSTM Model in PyTorch.

We explored audio interpolation & translation on four types of generative models: VAE, ACAI, MelGAN-VC, and BiGAN.

MNIST equivalent for audio

Foundation of Software Design and Development

This is a personal project implementing Convolutional Neural Networks (CNNs) and Variational Autoencoder (VAE) for sound generations

Spoken Digit Recognition with Machine learning methods