Double-attention mechanism of sequence-to-sequence deep neural networks for automatic speech recognition
- Authors
- Yook, Dongsuk; Lim, Dan; Yoo, In-Chul
- Issue Date
- 2020
- Publisher
- ACOUSTICAL SOC KOREA
- Keywords
- Attention; Sequence-to-sequence; Deep neural network; Automatic speech recognition
- Citation
- JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, v.39, no.5, pp.476 - 482
- Indexed
- SCOPUS
KCI
- Journal Title
- JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA
- Volume
- 39
- Number
- 5
- Start Page
- 476
- End Page
- 482
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/59027
- DOI
- 10.7776/ASK.2020.39.5.476
- ISSN
- 1225-4428
- Abstract
- Sequence-to-sequence deep neural networks with attention mechanisms have shown superior performance across various domains, where the sizes of the input and the output sequences may differ. However, if the input sequences are much longer than the output sequences, and the characteristic of the input sequence changes within a single output token, the conventional attention mechanisms are inappropriate, because only a single context vector is used for each output token. In this paper, we propose a double-attention mechanism to handle this problem by using two context vectors that cover the left and the right parts of the input focus separately. The effectiveness of the proposed method is evaluated using speech recognition experiments on the TIMIT corpus.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School > Department of Computer Science and Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.