Kaldi DNN Simple Notes

Jump to bottom

Ben Chen edited this page Aug 3, 2017 · 3 revisions

Kaldi Deep Nerual Net

References

How to Train a Deep Neural Net Acoustic Model with Kaldi

Intro

Labeled frames(phoneme-to-audio alignements) generated by a GMM-HMM system are needed for DNN trainning.

Directories needed

data/train (generated by local/prepare_data.sh)
data/lang (generated by local/prepare_lang.sh)
exp/tri*_ali (generated by align_si.sh)
mfcc (generated by make_mfcc.sh)

Train

steps/nnet2/train*.sh

obligatory arguments are:

data/train (the trainning data)
data/lang (the language dir)
exp/tri*_ali (the alignments from the previous GMM-HMM model)
$exp_dir (for DNN model to output to)

Decode

steps/nnet2/decode*.sh

6 args:

exp/tri\*/graph (the decoding graph from the GMM-HMM)
data/test (the test data)
$exp_dir/final.mdl (trained DNN acoustic model
UNK (the unknown phone)
SIL (the silence phone
$exp_dir/decode (new dir to save decoding info in (lattices, etc))

utils/best_wer.sh Get the score from the results.

Home	Kaldi	Kaldi DNN Simple Notes	Some Unix Commands	Perl Basics

Kaldi

Overview	Data Preperation	Extract MFCC features	Train monophone models	Align audio with the acoustic models	Train triphone models	Re-align audio with the acoustic models & re-train triphone models	Kaldi DNN Simple Notes