The Future of Sound Control: Shape-Changing Smart Speakers Divide Rooms with Self-Deploying Microphones
Virtual meetings have solved the problem of people talking over each other with the simple press of a mute button. But when it comes to in-person gatherings, this ability is not so easily translated. In a crowded cafe, there are no buttons to silence the table beside you. However, researchers at the University of Washington have come up with a solution: a shape-changing smart speaker.
The Innovative Technology
The shape-changing smart speaker uses self-deploying microphones to divide rooms into speech zones and track the positions of individual speakers. With the help of deep-learning algorithms, this system allows users to mute certain areas or separate simultaneous conversations, even if two adjacent people have similar voices.
Similar to a fleet of Roombas, each microphones are about an inch in diameter and automatically deploy from a charging station. This unique feature allows the system to be easily moved between environments and set up automatically. This means that in a conference room meeting, for example, this system could be deployed instead of a central microphone, providing greater control over in-room audio.
The Breakthrough
The team of researchers at the University of Washington published their findings in Nature Communications on September 21, showcasing the impressive capabilities of their robotic ‘acoustic swarm.’ This technology is the first to accurately distribute a robot swarm using only sound, eliminating the need for cameras, projectors, or special surfaces.
By emitting a high frequency sound, each of the seven small robots in the swarm is able to navigate and move around obstacles without falling off the table. The robots automatically disperse across tables to maximize accuracy and greater sound control. This allows for the system to differentiate and locate individual speakers more easily.
The Potential Applications
The team tested the prototype in various environments, including offices, living rooms, and kitchens, with groups of three to five people speaking. The system was able to discern different voices within 1.6 feet (50 centimeters) of each other 90% of the time, without any prior information about the number of speakers. Although the processing time was not fast enough for real-time communication, it was suitable for live streaming.
As the technology continues to progress, researchers envision the deployment of acoustic swarms in smart homes. This would allow smart speakers to differentiate between different individuals, enabling only those in an “active zone” to vocally control devices such as a TV.
Future plans for the technology include developing microphone robots that can move around rooms instead of being limited to tables. The team is also exploring the possibility of creating real-world mute and active zones by emitting sounds, allowing people in different parts of a room to hear different audio.
Privacy Concerns
Addressing concerns about privacy, the researchers have taken several precautions. The microphones navigate using sound instead of an onboard camera, ensuring visibility and transparency. Additionally, all audio is processed locally as a privacy constraint rather than in the cloud, as commonly done with smart speakers. The system could actually benefit privacy by creating specific mute zones to prevent recording in certain areas.
The shape-changing smart speaker with self-deploying microphones is a significant advancement in sound control technology. With its ability to divide rooms into speech zones and track individual speakers, it opens up new possibilities for improved audio experiences in various settings.