AI-driven automatic audio mixing for live sports














‘That gives me goosebumps, it’s like actually being there’

‘You miss the tension on the TV, this brings it back’

‘The broadcast sound is like watching an old game but this sounds like being there live’

‘Brilliant! Just brilliant’

Accelerating innovation: Salsa Sound and the advance of intelligent audio

Speaking to SVG Europe, the co-founders of Manchester-based audio start-up Salsa Sound discuss the work they have done during the COVID-19 pandemic, and how the virus (and subsequent lack of fans in stadiums) has quickened the pace of technological change within sports broadcasting.

NWSL Makes Broadcast-Network Debut on CBS With Full REMI Workflow

Cohen and the CBS Sports operations team evaluated a number of vendors before selecting Salsa Sound, which provided simulated crowd noise for the opening games.

AV Magazine

AV Magazine: Highlights of a Man City game, to which virtual crowd sounds had been added using the vCROWD app from Salsa Sound, generated more than two million views in less than 24 hours.

SVG News

Salsa Sound Sees Virtual Crowds as the Right Sounds at the Right Time

Audio is derived from authentic sources and can match nuances of the game

Press Release: Salsa Sound vCROWD for NWSL

Press releaseTradefairsalsa sound press releaseGreat news! Salsa Sound has been selected by CBS Sports and Vista to provide virtual crowd sound for the NWSL Challenge Cup! Salsa’s innovative Crowd DJ technology creates responsive crowd sound for games that can easily respond to every event on the field in real time, making more engaging stadium sound for broadcast.

Broadcast Sport: Salsa Sound Brings Virtual Fans To NWSL

Salsa Sound Brings Virtual Fans To National Women’s Soccer League“It was important to us that Crowd DJ could be operated by anyone with a good understanding of the game, the intuitive multi-touch interface allows even non-audio professionals to rapidly control every nuance of a sports crowd … authentic goal sounds and near misses, even the ironic cheers when the away team makes a mistake create a more engaging and enjoyable experience for fans.” Full story

Resolution: Next-generation audio for live sports broadcast

Audio objects and personalisation: Salsa Sound’s Dr. Ben Shirley describes a unique automated tool to extract audio event content and location.

© Resolution Magazine

Resolution: Sports Special, Dennis Baxter

….Salsa’s algorithm is capable of detecting ball kicks that are virtually inaudible on the microphone feeds and is more reliable at recognizing sound events than our ears….

© Resolution Magazine

SVG Europe IBC2017

“What we are doing is specifically addressing an ongoing —and, until now, unsolved — challenge faced by object-based formats, such as Atmos, MPEG-H, and DTS-X,” he explains. “The object-based paradigm requires new approaches to audio production, and, until now, there have been no automated tools to extract objects either in terms of the content or the location.”

SVG Europe

Using any microphone configuration, SALSA automatically tracks and identifies on-pitch sounds, controls mixing console fader movements, and creates what is described as an “augmented sound experience”. The result, it is said, is that SALSA can automatically devise an immersive mix for both conventional linear and non-linear broadcast, and for more sophisticated object-based distribution…

Broadcast Bridge

SALSA Initiative Looks To Automate Live Audio Mixing Process

At NAB 2016, SALSA was demonstrated as part of a complete outside broadcast production workflow, from capture to reproduction. SALSA-identified objects were shown being extracted from the mix by the 3DAW system in Fairlight’s EVO.Live mixing console, and packaged into a linear MDA bitstream for contribution over SDI.

Broadcast Beat

Fairlight has collaborated DTS.Inc. and the University of Salford to develop a new approach to assist sound engineers with live sports productions. The Spatial Automated Live Sports Audio (SALSA) solution is a real-time automated mixing process that identifies the location of specific sound events from a grid of pitch microphones. The algorithm, developed by the University of Salford, identifies the …

For further information and demo requests, get in touch.