arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.05855cs.CLcs.SDeess.AS

A Fast-Converged Acoustic Modeling for Korean Speech Recognition: A Preliminary Study on Time Delay Neural Network

Sogang University（西江大学）

Hosung Park, Donghyun Lee, Minkyu Lim, Yoseb Kang, Juneseok Oh, Ji-Hwan Kim

备注：
6 pages, 2 figures
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑