ericbolo
ericbolo
I find the method which you mention from https://arxiv.org/pdf/1711.02212.pdf appealing. For the benefit of others in this thread I will outline the system: 1/ train a blstm with ctc loss...
As I was looking into the tf_clean branch, these other design questions came to mind: - do we start with the character-based or the acoustic model ? I have experience...
#193 #155 : before delving into online decoding, it might be a good idea to have a full working example of the tensorflow acoustic model with WFST. Do you agree...
update: currently training a forward LSTM with tensorflow, with different loss functions (CTC only, student-teacher loss, etc.). Looking ahead, I'm studying examples of online decoding. Kaldi has online feature extractors...
great, MFCCs it is then (for now) thank you