Andrew Maas

stanford_dl_ex. Programming exercises for the Stanford Unsupervised Feature Learning and Deep Learning Tutorial

stanford-ctc. Neural net code for lexicon-free speech recognition with connectionist temporal classification

rnn-speech-denoising. Recurrent neural network training for noise reduction in robust automatic speech recognition

lblDm-demo. Log-Bilinear Document Model

kaldi-web. Web server to connect Kaldi speech recognizers to real-time web clients