A Fast-Converged Acoustic Modeling for Korean Speech Recognition: A Preliminary Study on Time Delay Neural Network
2018-07-11Unverified0· sign in to hype
Hosung Park, Dong-Hyun Lee, Minkyu Lim, Yoseb Kang, Juneseok Oh, Ji-Hwan Kim
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
In this paper, a time delay neural network (TDNN) based acoustic model is proposed to implement a fast-converged acoustic modeling for Korean speech recognition. The TDNN has an advantage in fast-convergence where the amount of training data is limited, due to subsampling which excludes duplicated weights. The TDNN showed an absolute improvement of 2.12% in terms of character error rate compared to feed forward neural network (FFNN) based modelling for Korean speech corpora. The proposed model converged 1.67 times faster than a FFNN-based model did.