There are 2 repositories under dnn-hmm topic.
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
:fire: ASR教程: https://dataxujing.github.io/ASR-paper/
A Deep LSTM-CNN-HMM Neural Network system for Speaker Identification
Implementation of Neural Networks in Theano for MNIST and AN4 dataset