Sound recognition from machine learning

• Main Author: Xiong, Ziqin
• Other Authors: Jiang Xudong
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/150525
• Institution: Nanyang Technological University

Audio event detection has always been a hot research field of acoustics com- bined with computer science. The research of audio event detection has impor- tant academic significance and commercial value. With the development of ma- chine learning and artificial intelligence, more and more machine learning and deep learning methods have been used in audio event detection, and achieved good results. In recent years, the success of self attention mechanism in the field of computer vision and natural language processing proves that self atten- tion mechanism has great potential. In this dissertation, self attention mechanism (CBAM) is transferred to the field of audio event detection, and theoretical ex- ploration and experimental proof are carried out.