Salsa Sound launches MIXaiR 2.0, a software version of the live spatial audio mixer for sports broadcasting – rAVe [PUBS]
Salsa Sound released version 2.0 of MIXaiR to provide multiple automated spatial audio mixes for the same listening experience, whether with headphones or speaker setups. It does not require any tracking or manual operation as the system takes audio streams from existing broadcast microphones in a stadium. It relies on AI algorithms to detect, mix and enhance sounds in the field and create real-time mixes.
Salsa Sound claims its AI-powered solution offers broadcasters and sports organizations a way to create automated mixes and is designed to speed up audio workflows, automatically rendering multiple formats and mixing multiple language versions or flavors. crowds (eg home / outdoors). Each mix is automatically made to conform to the required loudness standards and parameters required for social media platforms, linear broadcasting, VOD or OTT.
MIXaiR 2.0 has been “trained” with hundreds of hours of Premier League and English Championship game content to learn what sounds make up a good mix. The system automatically recognizes important audio moments in the game and can automatically reduce profanity from field-side microphones entering the broadcast.
The latest version of MIXaiR takes its technology from a 1RU hardware offering to a pure software solution that supports all major operating systems (macOS, Linux, Windows, etc.) as well as virtual machines and platforms. cloud shapes. This solution is scalable, cost effective, and can be deployed onsite as part of a remote production workflow, over IP, or in the cloud.
Here is a video of how it works: