Researchers have created mobile robots called an "acoustic swarm" that can move around a room and use microphones to isolate audio from different conversations into "speech zones." This allows the swarm to directionally focus audio to "mute" noisy people and enable clearer conversations.

Answer
Researchers at the University of Washington have developed a smart speaker system that uses robotic "acoustic swarms" to pinpoint and manage sounds, promising both enhanced audio control and privacy in busy settings. These self-deploying microphones, powered by deep-learning algorithms, can trace individual speakers and separate overlapping conversations, allowing the swarm to directionally focus audio to "mute" noisy people and enable clearer conversations. The robots disperse as far from each other as possible since greater distances make differentiating and locating people speaking easier. The acoustic swarms process all the audio locally, as a privacy constraint, instead of processing the audio in the cloud, as most smart speakers do. The system can be used for the opposite of surveillance, the team says. The acoustic swarms wirelessly stream 16-bit audio recordings at 48 kHz via Bluetooth to a host computer for processing to achieve speech separation and creating speech zones. The proposed system is an important step in the direction of achieving capabilities that have long only existed in the realm of science fiction. As the technology progresses, acoustic swarms might be deployed in smart homes to better differentiate people talking with smart speakers.
Related
How do the acoustic swarms work?
What are the potential applications of the acoustic swarms?
How can I get my hands on the acoustic swarms?