kaldi上拓展的深度学习（Kaldi+PDNN）

    这个是昨晚无意中的发现，由于远在cmu大学的苗亚杰（Yajie Miao）博士的贡献，我们又可以在kaldi上使用深度学习的模块。之前在htk上使用dbn一直还没成功，希望最近可以早点实现。以下是苗亚杰博士的主页上的关于kaldi+pdnn的介绍。希望大家可以把自己的力量也贡献出来，让我们作为学生的多学习学习。

Kaldi+PDNN -- Implementing DNN-based ASR Systems with Kaldi and PDNN
Overview
Kaldi+PDNN contains a set of fully-fledged Kaldi ASR recipes, which realize DNN-based acoustic modeling using the PDNN toolkit. The overall pipeline has 3 stages:       1. The initial GMM model is built with the existing Kaldi recipes        2. DNN acoustic models are trained by PDNN        3. The trained DNN model is ported back to Kaldi for hybrid decoding or further tandem system building
Hightlights
Model diversity. Deep Neural Networks (DNNs); Deep Bottleneck Features (DBNFs); Deep Convolutional Networks (DCNs)       PDNN toolkit. Easy and fast to implement new DNN ideas      Open license. All the codes are released under Apache 2.0, the same license as Kaldi      Consistency with Kaldi. Recipes follow the Kaldi style and can be integrated seemlessly with the existing setups
Release Log
Dec 2013  ---  version 1.0 (the initial release) Feb 2014  ---  version 1.1 (clean up the scripts, add the dnn+fbank recipe run-dnn-fbank.sh, enrich PDNN)
Requirements
1. A GPU card should be available on your computing machine.        2. Initial model building should be run, ideally up to train_sat and align_fmllr       3. Software Requirements:       * Theano. For information about Theano installation on Ubuntu Linux, refer to this document editted by Wonkyum Lee from CMU. * pfile_utils. This script (that is, kaldi-trunk/tools/install_pfile_utils.sh) installs pfile_utils automatically.
Download
Kaldi+PDNN is hosted on Sourceforge. You can enter your Kaldi Switchboard setup (such as egs/swbd/s5b) and download the latest version via svn:      svn co svn://svn.code.sf.net/p/kaldipdnn/code-0/trunk/pdnn pdnn svn co svn://svn.code.sf.net/p/kaldipdnn/code-0/trunk/steps_pdnn steps_pdnn svn co svn://svn.code.sf.net/p/kaldipdnn/code-0/trunk/run_swbd run_swbd ln -s run_swbd/* ./       Now the new run-*.sh scripts appear in your setup. You can run them directly.
Recipes
run-dnn.sh DNN hybrid system over fMLLR features   Targets: context-dependent states from the SAT model exp/tri4a      Input: spliced fMLLR features       Network:  360:1024:1024:1024:1024:1024:${target_num}      Pretraining: pre-training with stacked denoising autoencoders         run-dnn-fbank.sh DNN hybrid system over filterbank features   Targets: context-dependent states from the SAT model exp/tri4a      Input: spliced log-scale filterbank features with cepstral mean and variance normalization      Network:  330:1024:1024:1024:1024:1024:${target_num}      Pretraining: pre-training with stacked denoising autoencoders        run-bnf-tandem.sh GMM Tandem system over Deep Bottleneck features   [ reference paper ]   Targets: BNF network training uses context-dependent states from the SAT model exp/tri4a      Input: spliced fMLLR features      BNF Network: 360:1024:1024:1024:1024:42:1024:${target_num}      Pretraining: pre-training the prior-to-bottleneck layers (360:1024:1024:1024:1024) with stacked denoising autoencoders        run-bnf-dnn.sh DNN hybrid system over Deep Bottleneck features   [ reference paper ]   BNF network: trained in the same manner as in run-bnf-tandem.sh      Hybrid Input: spliced BNF features      BNF Network: 378:1024:1024:1024:1024:${target_num}      Pretraining: pre-training with stacked denoising autoencoders       run-cnn.sh Hybrid system based on deep convolutional networks (DCNs)  [ reference paper ]   The CNN recipe is not stable. Needs more investigation.       Targets: context-dependent states from the SAT model exp/tri4a      Input: spliced log-scale filterbank features with cepstral mean and variance normalization; each frame is taken as an input feature map      Network:  two convolution layers followed by three fully-connected layers. See this page for how to config the network structure.      Pretraining: no pre-training is performed for DCNs
Experiments & Results
The recipes are developed based on the Kaldi 110-hour Switchboard setup. This is the standard system you can get if you run egs/swbd/s5b/run.sh. Our experiments follow the similar configurations as described inthis paper. We have the following data partitions. The "validation" set is used to measure frame accuracy and determine termination in DNN fine-tuning.       training -- train_100k_nohup (110 hours)         validation -- train_dev_nohup        testing -- eval2000 (HUB5'00) Recipes WER% on HUB5'00-SWB WER% on HUB5'00 run-dnn.sh           19.3        25.7 run-dnn-fbank.sh           21.4        28.4 run-bnf-tandem.sh           TBA        TBA run-bnf-dnn.sh           TBA        TBA run-cnn.sh           TBA        TAB Our hybrid recipe run-dnn.sh is giving WER comparable with this paper (Table 5 for fMLLR features). We are confident to think that our recipes perform comparably with the Kaldi internal DNN setups.
Want to Contribute?
We look forward to your contributions. Improvement can be made on the following aspects (but not limited to):      1. Optimization to the above recipes 2  New recipes 3. Porting the recipes to other datasets 4. Experiments and results 5. Contributions to the PDNN toolkit   Contact Yajie Miao ([email protected]) if you have any questions or suggestions.

上述就是苗博士的介绍。具体可见：http://www.cs.cmu.edu/~ymiao/kaldipdnn.html。

   此外，该实验需要的配置是GPU，有GPU的同学可以仿真实现下。此外，PDNN是基于Theano上的python编写的，需要大家熟悉下Python语言。kaldi安装过程中遇到的问题可以参见我之前的博客。希望可以和大家多多交流……