For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Channel and Frequency Attention Module for Diverse Animal Sound Classification
Kyungdeuk KO Jaihyun PARK David K. HAN Hanseok KO
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2019/12/01
Online ISSN: 1745-1361
Type of Manuscript: LETTER
Category: Artificial Intelligence, Data Mining
artificial intelligence, deep learning, acoustic signal, self-attention, CNN,
Full Text: PDF>>
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.