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.
Two-stage Training for Chinese Dialect Recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this paper, we present a two-stage language identification (LID) system based on a shallow ResNet14 followed by a simple 2-layer recurrent neural network (RNN) architecture, which was used for Xunfei (iFlyTek) Chinese Dialect Recognition Challenge and won the first place among 110 teams. The system trains an acoustic model (AM) firstly with connectionist temporal classification (CTC) to recognize the given phonetic sequence annotation and then train another RNN to classify dialect category by utilizing the intermediate features as inputs from the AM. Compared with a three-stage system we further explore, our results show that the two-stage system can achieve high accuracy for Chinese dialects recognition under both short utterance and long utterance conditions with less training time.
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.