Repo associated to the DESED dataset, download and creation of data

Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.

A fast parallel implementation of RNN Transducer.

TensorFlow documentation

Notes on Machine Learning on edge for embedded/sensor/IoT uses

Learning associations between human faces and voices

Using LSTMs to exploit any temporal structure in noise.

DRNN with LSTM for monaural source separation

Collection of custom layers and utility functions for Keras which are missing in the main framework.

A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.