Multi-Channel Speech Denoising for Machine Ears

no code implementations • 17 Feb 2022 • Cong Han, E. Merve Kaya, Kyle Hoefer, Malcolm Slaney, Simon Carlile

This work describes a speech denoising system for machine ears that aims to improve speech intelligibility and the overall listening experience in noisy environments.

Denoising Speech Denoising

Neural Architecture Search for Energy Efficient Always-on Audio Models

no code implementations • 9 Feb 2022 • Daniel T. Speckhard, Karolis Misiunas, Sagi Perel, Tenghui Zhu, Simon Carlile, Malcolm Slaney

Mobile and edge computing devices for always-on classification tasks require energy-efficient neural network architectures.

Audio Classification Edge-computing +2