Channel and Frequency Attention Module for Diverse Animal Sound Classification
- Authors
- Ko, Kyungdeuk; Park, Jaihyun; Han, David K.; Ko, Hanseok
- Issue Date
- 12월-2019
- Publisher
- IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG
- Keywords
- artificial intelligence; deep learning; acoustic signal; self-attention; CNN
- Citation
- IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, v.E102D, no.12, pp.2615 - 2618
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
- Volume
- E102D
- Number
- 12
- Start Page
- 2615
- End Page
- 2618
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/61301
- DOI
- 10.1587/transinf.2019EDL8128
- ISSN
- 1745-1361
- Abstract
- In-class species classification based on animal sounds is a highly challenging task even with the latest deep learning technique applied. The difficulty of distinguishing the species is further compounded when the number of species is large within the same class. This paper presents a novel approach for fine categorization of animal species based on their sounds by using pre-trained CNNs and a new self-attention module well-suited for acoustic signals The proposed method is shown effective as it achieves average species accuracy of 98.37% and the minimum species accuracy of 94.38%, the highest among the competing baselines, which include CNN's without self-attention and CNN's with CBAM, FAM, and CFAM but without pre-training.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.