Deep Neural Network Model (AUDIO) The Zuckerman Institute at Columbia University Your browser does not support the audio element. Caption This is a representation of Dr. Mesgarani's new approach that uses a vocoder and deep neural network to reconstruct speech. Credit Nima Mesgarani/Columbia's Zuckerman Institute Usage Restrictions Please contact Zuckerman Institute press office for permissions. License Licensed content Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.