Immersive technology startup, Gaudio Lab (CEO Hyun-oh Oh), introduced Audiotech at the 'Naver D2SF Media Meet-up' held at the Naver D2SF office in Seocho-gu, Seoul on the 17th.

Gaudio Lab is an audio specialized technology startup where they do research and development to provide an outstanding sound experience by 20 audio experts, including 7 Ph.D. in sound engineering. They have developed ▲ 'AI Source Separation' that can separate voices, background sounds, and instrument sounds from sound files with AI technology ▲ 'AI Text Sync', a solution that automatically synchronizes lyrics and sound sources to provide real-time lyrics viewing ▲ 'Loudness Normalization' to reduce the volume deviation between contents and provide a balanced listening environment when listening to OTT/music streaming.

At this media meet-up, Gaudio Lab presented its plans to focus on the metaverse in the future and fill the technologies necessary for spatial sound. They mentioned that it is a problem that there is no sound in the current metaverse virtual space, and said that sound reproduction technology is needed so users can experience the space even in a virtual space.

To resolve this problem, Gaudio Lab started with the question: ‘What if AI could automatically create sound by just watching a video?’. They are developing and implementing sound sources needed for each space through ‘Project SSG’.