Atsushi Marui, Toru Kamekawa, Chihiro Nagashima, and Homare Kon (from left to right). The photo was taken by Kazutsugu Simon Uchimura.
Four presenters each reported their experiences in the 144th Convention held in Milan, Italy. Dr. Marui introduced the general overview of the society and the convention, followed by Mr. Kon's and Dr. Kamekawa's detailed reports related to the foci of their research. As the president of Japan Student Section, Ms. Nagashima reported the student activities held in the convention.
Following Dr. Marui's brief introduction and the summary of the convention, Mr. Kon, who is a doctoral student focusing on the use of machine learning techniques such as Deep Learning for VR/AR audio applications, reviewed the eight papers presented in the conference that employed Deep Learning as a part of their studies. Since Deep Learning is still a new technique in Audio, his review including the overview of the technique itself was quite helpful in understanding one of the prominent directions in the field.
Dr. Kamekawa chose and introduced the papers, workshops, and tutorials related to his expertise in spatial audio and audio production. The advent of three-dimensional audio employing height channels (in discrete loudspeakers playback) or head-tracking (in headphone playback) is already a big trend since a few conventions ago and his review showed that it is now ripe.
Finally, Ms. Nagashima reported on the student activities organized by the Student Delegate Assembly. The report included the Recording Competition, Recording Critiques, Design Competition, and Career Development Events, as well as the events planned for the Spatial Audio Conference held in Tokyo in the early August.
