Dong Hyun Kim

Dong Hyun Kim
Electronics and Telecommunications Research Institute | ETRI · Automatic Speech Translation and Artificial Intelligence Research Center

About

2
Publications
144
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2
Citations
Citations since 2016
2 Research Items
2 Citations
20162017201820192020202120220.00.20.40.60.81.0
20162017201820192020202120220.00.20.40.60.81.0
20162017201820192020202120220.00.20.40.60.81.0
20162017201820192020202120220.00.20.40.60.81.0

Publications

Publications (2)
Article
Full-text available
In this paper, we propose a new method for code-switching (CS) automatic speech recognition (ASR) in Korean. First, the phonetic variations in English pronunciation spoken by Korean speakers should be considered. Thus, we tried to find a unified pronunciation model based on phonetic knowledge and deep learning. Second, we extracted the CS sentences...
Article
This paper explores new techniques that are based on a hidden‐layer linear transformation for fast speaker adaptation used in deep neural networks (DNNs). Conventional methods using affine transformations are ineffective because they require a relatively large number of parameters to perform. Meanwhile, methods that employ singular‐value decomposit...

Network

Cited By