IoT Hardware: Apple’s new voice the HomePod

Smart Blog

IoT Hardware: Apple’s new voice the HomePod

Recently, deep learning has gained momentum the field of speech technology. Deep learning has also enabled a completely new approach for speech synthesis called direct waveform modeling, which has the potential to provide both the high quality of unit selection synthesis and flexibility of parametric synthesis. In order to provide the best possible quality for Siri’s voices across all platforms, computer scientists at Apple are now taking a step forward to utilize deep learning in an on-device hybrid unit selection system.

Apple HomePod IoT Hardware

Starting in iOS 10 and continuing with new features in iOS 11, Apple has announced that it will base Siri voices on deep learning. For iOS 11, Apple chose a new female voice talent with the goal of improving the naturalness, personality, and expressivity of Siri’s voice, thus hopefully leading to a wealth of new applications in voice-based human-machine interaction, for instance through the Apple HomePod smart speaker system, that is expected to be launched soon and that will go head-to-head with such popular products as Amazon Echo and Google Home.

Author: Tim Cole

Image Credit: Apple


Leave a Reply

Your email address will not be published. Required fields are marked *