Photo credit: April Hong/University of Washington
University of Washington researchers have developed a smart speaker that can change shape and use self-deploying microphones to divide rooms into speech zones. By tracking the positions of individual speakers combined with deep learning algorithms, the speaker can mute different sections of a room or separate simultaneous conversations.
The smart speaker measures in at around an inch in diameter and its microphones automatically deploy from, and then return to, a charging station. This means that the entire system can easily be moved between environments and set up automatically. For example, in conference meetings, these smart speakers can be deployed instead of a central microphone, enabling better control of in-room audio.
- Ultra-Portable 2" Tall Speaker
- Bluetooth 5. 0 Technology Wirelessly Connects to all Bluetooth Enabled Devices
- 30Ft. Wireless Range / Over 4 Hours of Music Time on a Single Charge. / Rechargeable - Micro USB Cable Included
If I have one microphone a foot away from me, and another microphone two feet away, my voice will arrive at the microphone that’s a foot away first. If someone else is closer to the microphone that’s two feet away, their voice will arrive there first. We developed neural networks that use these time-delayed signals to separate what each person is saying and track their positions in a space,” said Tuochao Chen, co-lead author and UW doctoral student in the Allen School.
