SMT007 Magazine


Issue link:

Contents of this Issue


Page 47 of 93

48 SMT007 MAGAZINE I AUGUST 2022 to deliberate and determine a fair way to run a community trading platform. Today, these companies collectively trade parts through a virtual stockroom combining the inventory of 60-plus OEM/EMS companies with more than 150,000 unique part numbers. Collaborative Problem Solving As one example, during the first year of the recent pandemic, we launched the virtual AccelerateEMS conference. With more than 350 attendees over two days, we saw over- whelming enthusiasm for what they learned and the connections they made. It is now a recurring event. We plan to host our third industry confer- ence, Aug. 30-31, in-person for the first time. We expect to see attendance from distributors, buyers, technologists, leaders, and visionaries. We are seeking to convene the best people in the industry, with the goal to learn and discuss these problems through roundtables, panels, and presentations. SMT007 References 1. Chintan Sutaria is founder and president of Calcu- quote, a quoting and supply chain software busi- ness serving more than 200 electronics manufac- turers in 25 countries. As meetings shifted online during the COVID-19 lockdown, many people found that chattering room- mates, garbage trucks and other loud sounds dis- rupted important conversations. This experience inspired three University of Wash- ington researchers, who were roommates during the pandemic, to develop better earbuds. To enhance the speaker's voice and reduce background noise, "ClearBuds" use a novel microphone system and one of the first machine-learning systems to operate in real time and run on a smartphone. ClearBuds use a dual microphone array. Micro- phones in each earbud create two synchronized audio streams that provide information and allow us to spatially separate sounds coming from differ- ent directions with higher resolution. Second, the lightweight neural network further enhances the speaker's voice. While most commercial earbuds also have micro- phones on each earbud, only one earbud is actively sending audio to a phone at a time. With ClearBuds, each earbud sends a stream of audio to the phone. The researchers designed Bluetooth networking protocols to allow these streams to be synchronized within 70 microseconds of each other. The team's neural network algorithm runs on the phone to process the audio streams. First it sup- presses any non-voice sounds. And then it isolates and enhances any noise that's coming in at the same time from both earbuds — the speaker's voice. "Because the speaker's voice is close by and approximately equidistant from the two earbuds, the neural network can be trained to focus on just their speech and eliminate background sounds, including other voices," said co-lead author Ishan Chatterjee, a doctoral student in the Allen School. "This method is quite similar to how your own ears work. They use the time difference between sounds coming to your left and right ears to determine from which direction a sound came from." When the researchers compared ClearBuds with Apple AirPods Pro, ClearBuds performed better, achieving a higher signal-to-distortion ratio across all tests. (Source: University of Washington) ClearBuds: First Wireless Earbuds That Clear up Calls Using Deep Learning The ClearBuds hardware (round disk) in front of the 3D printed earbud enclosures. (Raymond Smith/University of Washington)

Articles in this issue

Archives of this issue

view archives of SMT007 Magazine - SMT007-Aug2022