A two-stage CTC-trained acoustic model feeding a BLSTM classifier achieves 88.9 percent accuracy on ten Chinese dialects, beating a one-stage baseline by 10 percent.
We train an AM in the first stage and then use the intermediate features from the AM as inputs to train an RNN to compute posteriors for LID in the second stage
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Two-stage Training for Chinese Dialect Recognition
A two-stage CTC-trained acoustic model feeding a BLSTM classifier achieves 88.9 percent accuracy on ten Chinese dialects, beating a one-stage baseline by 10 percent.