Gismart at Big Data Hackathon!

Gismart has officially partnered with Datathon, Big Data & Data Science hackathon.

Datathon is a 6-day competition where talented teams come up with working solutions for real-life business challenges. They tackle challenges top companies operating in fields from finance to gaming mobile face every day. As a music tech hackathon partner, we were in charge of setting the task. We laid out the challenge to improve the clarity of vocal recordings in Karaoke Face using machine learning (ML) and artificial intelligence (AL) technology.

Karaoke Face is the first karaoke app that uses AR mask technology to let users create video and audio recordings. Due to imperfect acoustic conditions, vocal recordings are often interrupted by external noises. We challenged the contestant to provide a solution that diminishes or eliminates this issue!

Datathon participants worked with audio recordings that featured disruptive noises as well as constant background noise, to mimic a vocalist singing without headphones.

“Audio recording quality has been one of the main issues in Karaoke Face. We’ve recently established an in-house Research team, and a Development Department, to focus on this. Here we’ll look for the best tech solutions that ultimately improve the product and end-user experience. Datathon was an opportunity for us to meet the community, share our knowledge and see the solutions provided by the competing teams.” – Sergey Shchegrikovich, Director of Engineering at Gismart.

Gismart chose Team Enigma as the winner of Gismart challenge because they best met the criteria! Well done to Team Enigma.

If you haven’t had the chance to play Karaoke Face you can download it here, because who doesn’t love karaoke?