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. |