Got from zzw922cn/awesome-speech-recognition-papers.
Automatic speech recognition paper roadmap, including HMM, DNN, RNN, CNN, Seq2Seq, Attention
Automatic Speech Recognition has been investigated for several decades, and speech recognition models are from HMM-GMM to deep neural networks today. It's ver继续阅读 »
之前简单介绍过 LSTM，网址，本文将利用 LSTM 构建一个故事生成的模型。
我们使用的数据是 Aesop’s Fables 里的一部分内容，如下：
long ago , the mice had a general council to consider what measures they could take to outwit their common enemy , the cat . some said this , and some said that but at last a young mouse got up and said he had a proposal to make继续阅读 »
I got a good things on GitHub, and share it here. There are some classical papers about deep learning.
Deep learning (2015), Y. LeCun, Y. Bengio and G. Hinton [pdf] :sparkles:
Deep learning in neural networks: An overview (2015), J. Schmidhuber [pdf] :sparkles:
Representation learning: A review and new 继续阅读 »
This blog is reprinted from colah's blog and some changes are added by myself.
Humans don’t start their thinking from scratch every second. And traditional neural networks have a major shortcoming, and they cannot learn from the previous information. Recurrent neural networks (RNN) address this issue.
本文翻译和总结与 kaldi.org。本文主要介绍 kaldi 代码的组织结构以及依赖结构，以及一些修改和调试代码的经验。如果想更深入了解，可以点击这里。
进入 src/base/，查看 kaldi-common.h，其内容主要为下：
define KALDI_BASE_KALDI_COMMON_H_ 1
include // C string stuff like strcpy