■ Seminar Overview
This lecture is intended for those who have theoretical knowledge and implementation experience in deep learning but have no experience in acoustic signal processing.
Against the backdrop of improved text and image processing capabilities in large language models, research on audio signals is gaining momentum as the next modality. Incorporating both research and practical perspectives, the learning objectives are for participants to be able to determine guidelines when tackling real-world problems and to understand the summaries of recent research papers.
【Date and Time】
8/1 (Thu), 8/2 (Fri) 13:00-15:00
Number of sessions: 4 in total (2 sessions per day x 2 days)
【Venue】
Hiyoshi Campus, Kyoseikan Collaboration Complex 2nd Floor, AIC Lounge
【Format】
In-person
*There are no plans for recording or online streaming.
【Prerequisites】
Basic theoretical knowledge of deep learning and implementation experience are required.
In particular, those who have no experience with image processing using CNNs are recommended to try implementing it once.
【What to Bring】
Since we will be processing sound, having earphones or headphones will help deepen your understanding.
【Target Audience】
Keio students, faculty and staff
【Organizer, etc.】
AIC
Please see here for details regarding application contents and other information.