Closed xfwu closed 7 years ago
Hi, discriminative training of CTC models is on our agenda. But we don't have an exact time when it can be delivered.
Thank you very much!
I have a few questions regarding MPE CTC.
1> Traditional MPE/sMBR employ posterior probabilities like in the SMBR paper
Sequence-discriminative training of deep neural networks
Equation 8 But CTC employs Maximum Likelihood Training. Can I use p(l|x) in
Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks
Equation 15 to replace the P(O|S) in SMBR paper Equation 8?
2>P(W) (in SMBR paper equation 15) supposed to be the language model of the training data, right? What if the training data and the real test data are in different domain, I still need to use the language model of the training data?
Thank you very much
Hi Yajie
Sorry to bother you with another question:
The basic steps of discriminative training is
- get the denlattice
- get the alignment
- do the discriminative training
For step 1. my understanding is the CTC lattice generated by latgen-faster For step 2. I don't have very clear clue how to get the aligment
Could you please give me some guidance?
Best
Hi Yajie
Just wondering if Eesen has this implementation plan? Thank you very much
Best