Last year, while at the Google I/O 2018 developer conference, Google previewed the John Legend’s voice as one of six new Google Assistant voices that were in the works. Thanks to Google’s DeepMind artificial intelligence and speech synthesis model WaveNet, Google can easily sample human speech, thereby cutting down on studio time, and still create realistic-sounding voices.
WaveNet
New Google Assistant Sounds More Human
Last year, artificial intelligence (AI) research company DeepMind shared details on WaveNet, a deep neural network used to synthesize realistic human speech. Now, an improved version of the technology is being rolled out for use with Google Assistant.
You must be logged in to post a comment.