In a technical paper scheduled to be presented next month at the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), a group of Amazon researchers propose an AI approach to multiple-source localization, or the problem of estimating a sound’s location using microphone audio. They say that in experiments involving real and simulated data (the former from the AV16.3 corpus) and up to three simultaneously active sound sources, it showed an improvement of nearly 15% compared with a state-of-the-art signal-processing model.
Addressing multiple-source localization is an indispensable step in developing sufficiently robust smart speakers, smart displays, and even videoconference software. That’s because it’s at the core of beamforming, a technique that focuses a signal (in this case sound) toward a receiving device (microphones). Amazon’s own