The latest update to the Crestron Automate VX speaker tracking solution adds visual AI for a best-in-class meeting experience

Jan. 23, 2024 - Since its introduction in 2017, the Automate VX speaker tracking solution has relied on audio location data. The results have been impressive, but the team knew there were greater possibilities ahead, advancements that could really make a difference for high-impact, high-occupancy meeting spaces.

The latest update to the software — version 6.1 — brings with it what may be the most important advancement yet: speaker tracking with visual AI.

Simply put, the artificial intelligence that drives this update makes for an even better experience for those collaborators who are joining a meeting remotely. It’s the latest step in our ongoing efforts to create true meeting equity in the hybrid work environment.

Visual AI: Auto-Framing and Reframing

Visual AI extends the power of Automate VX's speaker tracking by auto-framing the speaker, centering them in the frame even if they move from a position where a microphone has been sending location data. This frees collaborators to move naturally about the room as they speak — an especially common occurrence in longer meetings — without participants having to concern themselves with “staying in the frame.”

The “reframing” function that’s part of this update is one of the keys to its success: As people move around a space, they’ll be centered in the shot. This is where the AI solution shines, since it’s able to discern between slight movements — where no reframing is necessary — and larger moves. There’s no constant reframing if a speaker shifts slightly in their seat, for example, and this prevents unnecessary camera movements that could trigger motion sickness for some viewers.

Settings such as shot widths and “head height” are customizable, too — the system can be tailored for any user, any meeting, any space.

Add this update to the expanding list of benefits that come with the Automate VX speaker tracking solution, and it’s clear that the system is perfect for any organization’s high-impact spaces. Just ask the team at Microsoft.

As Crestron works to find ever-better answers to the challenges of the hybrid workplace, solutions such as Automate VX have been at the forefront. Since the heart of the solution is software-driven, advances such as this one can be deployed using existing hardware. The five-plus years of experience that the Crestron team brings to this specific system means that we’ve learned a lot — and all of that knowledge informs every update we make.

Optical Zoom: The Superior Choice

The Automate VX speaker tracking solution utilizes multiple cameras (up to 12) throughout a meeting space to ensure that remote viewers always get the right view as the conversation moves from person to person. It provides clear, crisp shots of every person in the room via the 1 Beyond cameras’ optical zoom technology. Instead of digital zooming, which enlarges and crops a portion of an image, reducing pixel density and image clarity, optical zooming occurs in the camera lens itself, bringing the viewer sharp images that capture every gesture and expression — even at a distance of 60 feet.

Broadcast Quality — Automated

Since the solution is creating a broadcast-quality video connection that’s completely automated, in-person attendees never have to concern themselves with looking toward the camera. The “cuts” between speakers mimic those you’d find in any film or TV program — they’re quick and clean, and eliminate constant camera movements such as panning, tilting, and zooming. The system includes settings such as Conversation Mode, which tracks both a current and previous speaker as two individuals conduct a dialog — allowing remote attendees to see non-verbal cues from each.

The result: A natural experience for every attendee, both remote and in-person.

Stellar Audio

Since the Automate VX speaker tracking solution began as a system that relied on microphone location to key on collaborators, its audio portion has been developed to provide the best possible experience. We've also built close relationships with the leading microphone and digital signal processing manufacturers, and we’re constantly broadening the number of products supported by the Automate VX system. The solution provides outstanding audio without aural clutter, helping to dampen extraneous noises such as coughs or papers rustling — and the system has “learned” not to recognize those noises as speech.

The Room Designer

The system’s extremely flexible and adaptable to any room layout. Our web-based utility, the Intelligent Video Room Designer, allows you to configure rooms ahead of time — even before purchasing any hardware. You're able to put the cameras and the microphones in a virtual room with a simple drag-and-drop function, determine what your various shots are going to look like, and adjust as necessary. Once you have the room configured to your liking, you're then able to take that data and provide it to the key stakeholders and decision-makers for that room prior to actually purchasing the system. Couple that with Crestron’s in-person and online support options, and a successful deployment is assured.

Additionally, the Automate VX solution is certified for Microsoft Teams® software and supports Zoom Rooms® software — or any other conferencing platform. It’s all part of Crestron’s commitment to helping you create best-in-class solutions for any room in your organization.